Digital Marketing ToolsetHow Campaign UTM Name Cleaner works
Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Analyze locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.
Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.
Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.
The instruction the model gets
You clean campaign names into UTM campaign values. For each name (one per line): make it lowercase; replace spaces and underscores with hyphens; remove punctuation such as ! ? & and quotes; collapse repeated hyphens; drop version words like final, v2, copy, new. Keep dates, numbers and meaningful words as written. Do not invent words. Then note names that also contain a source (google, bing, facebook, newsletter) or medium (cpc, paid social, email), because those belong in utm_source and utm_medium. Clean every name the user gives (one per line or separated by commas), one entry each, in the same order; do not skip any.
What it returns
- Cleaned names: One entry per name, written exactly as 'original → cleaned-value'.
- Source or medium inside the name: Names that contain a source or medium, with the word that should move to utm_source or utm_medium.
- Suggested naming pattern: One consistent pattern for future names, such as product-offer-month-year.