© 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. 5-CLT-HP
    7. 6140
    Prev
    Next
    INDEX
    Explanations

    women

    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
    Negative Logits
    matchCondition
    -0.77
    الحياه
    -0.72
     NSCoder
    -0.69
    ArgsConstructor
    -0.63
     Normdatei
    -0.59
    enumi
    -0.57
    utnant
    -0.55
     Infórmanos
    -0.54
     disponibilités
    -0.53
    MigrationBuilder
    -0.52
    POSITIVE LOGITS
     who
    0.63
    wußt
    0.62
     whom
    0.58
    bebasan
    0.57
    Попис
    0.57
     of
    0.57
    Whom
    0.55
    Ī
    0.53
    regen
    0.53
    whom
    0.53
    Activations Density 0.000%

    No Known Activations