© 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. 1-CLT-HP
    7. 10280
    Prev
    Next
    INDEX
    Explanations

    cut

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cut
    -0.61
    addCriterion
    -0.56
    ']?>
    -0.55
    CUT
    -0.54
    ண்ட
    -0.54
     Cut
    -0.52
     '\\;'
    -0.51
    DoubleQuotes
    -0.50
    +:+
    -0.49
    Cut
    -0.49
    POSITIVE LOGITS
    úrese
    0.60
    contentLoaded
    0.57
    setupUi
    0.57
    localctx
    0.52
    saraba
    0.52
    gameserver
    0.52
    VertexArray
    0.49
     estekak
    0.49
     esternos
    0.48
    NamedQueries
    0.48
    Activations Density 0.522%

    No Known Activations