© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and history

    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
     vii
    -1.05
     viii
    -0.79
    viii
    -0.65
    vii
    -0.63
    Diwedd
    -0.62
    windowFixed
    -0.61
    IVEREF
    -0.59
    SharedDtor
    -0.59
    nya
    -0.59
     xii
    -0.58
    POSITIVE LOGITS
     XVI
    0.59
    ⁡
    0.56
     XIX
    0.53
     rowspan
    0.52
    jooq
    0.50
     noqa
    0.47
    Lanz
    0.47
     pinulongan
    0.47
     II
    0.46
    jsonp
    0.45
    Activations Density 0.012%

    No Known Activations