© 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. 16030
    Prev
    Next
    INDEX
    Explanations

    government or molecules

    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
     minister
    -0.56
     ministers
    -0.52
     ministerial
    -0.51
    DATABASE
    -0.50
     molecular
    -0.48
     Pledge
    -0.48
    Toolbox
    -0.47
     logger
    -0.46
    minist
    -0.46
    hom
    -0.46
    POSITIVE LOGITS
    帖最后由
    0.93
    findpost
    0.82
    клопе
    0.81
    GEBURTSDATUM
    0.79
    verifyException
    0.77
    ConstraintMaker
    0.77
     autorytatywna
    0.76
    ьаж
    0.71
    Personensuche
    0.71
     Wikimedijinoj
    0.68
    Activations Density 0.054%

    No Known Activations