© 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. 11840
    Prev
    Next
    INDEX
    Explanations

    building

    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
    ollectionView
    -0.48
    fehlung
    -0.47
     preocupação
    -0.44
     riêng
    -0.42
    ękuję
    -0.42
    üyor
    -0.41
     unterwegs
    -0.41
    jspx
    -0.41
     diikuti
    -0.41
    entuh
    -0.41
    POSITIVE LOGITS
    %</
    0.72
     BoxDecoration
    0.71
     initComponents
    0.70
    MENAFN
    0.69
    :✨
    0.69
     مرئيه
    0.66
     mergeFrom
    0.62
    UVWXYZ
    0.61
     NSCoder
    0.61
    createClass
    0.60
    Activations Density 0.012%

    No Known Activations