© 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. 71397
    Prev
    Next
    INDEX
    Explanations

    General text

    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
    enumii
    -0.68
    featureID
    -0.66
    पया
    -0.53
    Obrázky
    -0.52
    principalTable
    -0.50
     nakalista
    -0.50
    pushFollow
    -0.48
    Ծանոթ
    -0.47
    ViewFeatures
    -0.47
     StatefulWidget
    -0.46
    POSITIVE LOGITS
    Xna
    0.60
    psack
    0.58
    polated
    0.57
     sabo
    0.57
    TagHelper
    0.57
     Monfieur
    0.57
    kwds
    0.56
    himovic
    0.54
     Efq
    0.54
    ectl
    0.53
    Activations Density 0.000%

    No Known Activations