© 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. 1-CLT-HP
    7. 8657
    Prev
    Next
    INDEX
    Explanations

    music

    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
    ArgsConstructor
    -0.62
     Composer
    -0.59
    s
    -0.57
     HasFactory
    -0.56
    setFocus
    -0.54
    Cousin
    -0.52
    schwe
    -0.50
    openzeppelin
    -0.50
     morire
    -0.49
     yyr
    -0.48
    POSITIVE LOGITS
    elemField
    0.62
     المعرف
    0.56
     leaders
    0.52
     Chwiliwch
    0.51
    Rè
    0.50
    HasColumnType
    0.49
     isSet
    0.48
    Rüyada
    0.48
    leaders
    0.48
    Legenda
    0.47
    Activations Density 0.005%

    No Known Activations