© 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. 6317
    Prev
    Next
    INDEX
    Explanations

    by or using

    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
     ModelExpression
    -0.89
    RenderAtEndOf
    -0.88
    IntoConstraints
    -0.82
     للاسماء
    -0.74
    awtextra
    -0.74
     myſelf
    -0.71
    ThroughAttribute
    -0.68
     للمعارف
    -0.68
     فريبيس
    -0.67
     purpoſe
    -0.67
    POSITIVE LOGITS
     to
    0.46
     دیکھیے
    0.41
     of
    0.41
     Pública
    0.40
    </h5>
    0.37
     ber
    0.37
    gway
    0.36
    -
    0.36
    </em>
    0.36
     okaz
    0.35
    Activations Density 0.046%

    No Known Activations