© 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. 20-CLT-HP
    7. 71564
    Prev
    Next
    INDEX
    Explanations

    code processing

    np_max-act-logits · 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
     >=",
    -0.96
    новништво
    -0.85
     EconPapers
    -0.82
    WebServlet
    -0.71
    PerformLayout
    -0.70
     ModelExpression
    -0.69
    sizeCache
    -0.68
    UnusedPrivate
    -0.66
    KommentareTeilen
    -0.65
    Jeografia
    -0.65
    POSITIVE LOGITS
     is
    0.69
     means
    0.59
    UnknownFieldSet
    0.49
    means
    0.47
    itu
    0.45
     signals
    0.42
    chell
    0.42
    BindView
    0.41
    
    0.40
     indicates
    0.40
    Activations Density 0.001%

    No Known Activations