© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73349
    Prev
    Next
    INDEX
    Explanations

    Code, percentages, copyrights

    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
    expandindo
    -0.91
    parsedMessage
    -0.60
    Enllaces
    -0.59
     الحره
    -0.55
    abestanden
    -0.52
     Dép
    -0.51
    crollView
    -0.51
     Jérusalem
    -0.49
     }{@
    -0.47
    Hentet
    -0.47
    POSITIVE LOGITS
    itattu
    0.54
    %.
    0.54
    %',
    0.53
     ModelExpression
    0.52
     per
    0.52
    setCancelable
    0.50
    %).
    0.49
    IndentedString
    0.48
    ²/
    0.48
    %",
    0.47
    Activations Density 0.000%

    No Known Activations