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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2409
    Prev
    Next
    INDEX
    Explanations

    at

    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
    页面存档备份
    -0.52
     dust
    -0.50
     rodent
    -0.49
     coaches
    -0.49
     */;
    -0.48
    ")));
    -0.48
     pollution
    -0.47
     stress
    -0.47
    ?')
    -0.47
    "])
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    #
    0.65
    +#+#
    0.61
     typelib
    0.61
     this
    0.59
     AssemblyTitle
    0.58
    //
    0.57
    parsedMessage
    0.57
    WriteLiteral
    0.57
     BoxDecoration
    0.56
    Activations Density 0.004%

    No Known Activations