© 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. 6094
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ")));
    -0.66
     ModelExpression
    -0.63
    )";
    -0.62
    /");
    -0.62
     فريبيس
    -0.62
     ),
    -0.61
    aronder
    -0.60
    '));
    -0.59
    %");
    -0.59
    /');
    -0.56
    POSITIVE LOGITS
     wide
    0.74
    enumi
    0.63
     widest
    0.62
    wide
    0.62
     broadest
    0.61
    tagHelperRunner
    0.60
    Wide
    0.59
     broad
    0.59
     WIDE
    0.57
    :✨
    0.54
    Activations Density 0.002%

    No Known Activations