© 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. 10245
    Prev
    Next
    INDEX
    Explanations

    legal/psychological proceedings

    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
    /**
    -0.71
    TagMode
    -0.67
    CloseOperation
    -0.65
    \}_{
    -0.63
    adaptiveStyles
    -0.63
     RoutedEventArgs
    -0.60
     whiteColor
    -0.59
    tagext
    -0.59
    ContentLoaded
    -0.56
     {}));
    -0.55
    POSITIVE LOGITS
    oa̍t
    0.57
    rubin
    0.53
    y
    0.51
    ่าย
    0.51
     lenker
    0.49
    bootstrapcdn
    0.47
    ıza
    0.47
     denn
    0.46
     sia
    0.45
    raj
    0.45
    Activations Density 0.021%

    No Known Activations