© 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. 0-CLT-HP
    7. 95595
    Prev
    Next
    INDEX
    Explanations

    Acronyms and Names

    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
    CAP
    -0.93
     Ralph
    -0.85
    Ralph
    -0.75
     CAP
    -0.68
    .*")]
    -0.63
     transfieras
    -0.57
    ValueStyle
    -0.55
     ralph
    -0.54
     으로
    -0.52
    autoload
    -0.51
    POSITIVE LOGITS
     combineReducers
    0.60
    er
    0.58
    vician
    0.57
    πε
    0.55
    不信
    0.54
    ollection
    0.51
    ржа
    0.50
     NotFound
    0.49
    amata
    0.48
    ukone
    0.48
    Activations Density 0.272%

    No Known Activations