© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77317
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous text

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.87
    InitVars
    -0.80
    aarrggbb
    -0.80
    ніципалі
    -0.73
    findpost
    -0.72
     Majesté
    -0.71
     Jefus
    -0.71
    localctx
    -0.70
    Rüyada
    -0.70
    %\]
    -0.69
    POSITIVE LOGITS
    TagMode
    0.60
     market
    0.41
     henvisninger
    0.40
     site
    0.38
    l
    0.38
    лен
    0.38
    le
    0.37
    <eos>
    0.37
    an
    0.36
     closed
    0.36
    Activations Density 0.000%

    No Known Activations