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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43807
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     يتيمه
    -0.65
    jsdelivr
    -0.45
     consultato
    -0.45
     كومونز
    -0.44
    arrêt
    -0.44
    onStop
    -0.44
    stop
    -0.43
     Möglich
    -0.43
    rab
    -0.43
     tap
    -0.42
    POSITIVE LOGITS
     ſeveral
    0.73
     للاسماء
    0.69
    usschuss
    0.66
     himſelf
    0.65
     itſelf
    0.64
    例句
    0.63
     myſelf
    0.63
     useEffect
    0.62
    ']))
    0.62
     propOrder
    0.62
    Activations Density 1.766%

    No Known Activations