© 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. 8643
    Prev
    Next
    INDEX
    Explanations

    pitch

    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
     range
    -0.44
    .../
    -0.43
    toft
    -0.43
     T
    -0.43
     
    -0.42
    DeclareMath
    -0.41
     Lang
    -0.39
     spo
    -0.39
    nacht
    -0.38
    QObject
    -0.38
    POSITIVE LOGITS
    httphttps
    0.95
     myſelf
    0.94
     للاسماء
    0.93
     ſeveral
    0.87
     perfons
    0.84
     Efq
    0.84
     kasarigan
    0.83
     itſelf
    0.81
     Проци
    0.79
    Personensuche
    0.79
    Activations Density 0.059%

    No Known Activations