© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92142
    Prev
    Next
    INDEX
    Explanations

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cleaning
    -1.93
     Cleaning
    -1.66
     cleaner
    -1.64
    cleaning
    -1.63
    Cleaning
    -1.61
     CLEANING
    -1.58
     cleaned
    -1.54
     cleaners
    -1.54
     Cleaner
    -1.44
     cleans
    -1.41
    POSITIVE LOGITS
     médicale
    0.50
     hırka
    0.49
     thérape
    0.44
     medicamento
    0.44
     upraw
    0.44
    pulumi
    0.43
     médic
    0.43
     invasión
    0.43
     Coliseum
    0.42
     Drugs
    0.42
    Activations Density 0.200%

    No Known Activations