© 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. 91105
    Prev
    Next
    INDEX
    Explanations

    Polk

    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
     للاسماء
    -0.48
    ẤT
    -0.47
     وتسجيلات
    -0.44
    ValueStyle
    -0.44
    啶
    -0.43
     ddelweddau
    -0.43
     butterknife
    -0.42
    ("]");
    -0.41
     yako
    -0.41
    aneous
    -0.41
    POSITIVE LOGITS
    GIVEREF
    0.73
     InputDecoration
    0.70
     виправивши
    0.63
     propOrder
    0.54
    UnknownFieldSet
    0.54
    Capítulo
    0.54
    zzleHttp
    0.54
     ModelExpression
    0.53
     getRule
    0.53
     marche
    0.52
    Activations Density 0.000%

    No Known Activations