© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78071
    Prev
    Next
    INDEX
    Explanations

    9

    np_max-act-logits · 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
    Negative Logits
    клопе
    -0.69
    Pautan
    -0.59
    GraphicsUnit
    -0.54
    djangoproject
    -0.52
    MemoryWarning
    -0.50
    FormState
    -0.50
     dàng
    -0.49
    帖最后由
    -0.47
    FetchType
    -0.47
     {?>
    -0.47
    POSITIVE LOGITS
    nergy
    0.59
     Portuguesa
    0.58
     Jalan
    0.56
    upstream
    0.54
    իր
    0.54
    StoreMessageInfo
    0.54
    EDC
    0.53
    dtp
    0.53
    adhi
    0.52
    uela
    0.52
    Activations Density 0.000%

    No Known Activations