© 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. 5-CLT-HP
    7. 91839
    Prev
    Next
    INDEX
    Explanations

    import

    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
     चीज़ों
    -0.50
    makeConstraints
    -0.49
    Portály
    -0.49
    Javadoc
    -0.48
    tamil
    -0.47
     AssemblyCulture
    -0.47
    lavia
    -0.47
    plevel
    -0.47
    yeur
    -0.46
    extent
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.73
    ViewFeatures
    0.62
    !*\
    0.56
     Wikimedijinoj
    0.54
    matchCondition
    0.51
    ībā
    0.51
    )++;
    0.51
    parsedMessage
    0.51
    HasAnnotation
    0.51
    complexContent
    0.50
    Activations Density 0.004%

    No Known Activations