© 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. 0-CLT-HP
    7. 40302
    Prev
    Next
    INDEX
    Explanations

    Business, science, and law

    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
     works
    -0.48
     davantage
    -0.42
     also
    -0.40
    mayı
    -0.39
     vũ
    -0.39
     cuma
    -0.39
     juste
    -0.39
     just
    -0.38
    lepaskan
    -0.38
     recent
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.80
     Infórmanos
    0.78
    AnchorStyles
    0.76
    AndEndTag
    0.76
    ngdoc
    0.73
     dAtA
    0.73
    DoubleQuotes
    0.72
    FieldBuilder
    0.70
    parsedMessage
    0.70
     ويكيپيديا
    0.69
    Activations Density 0.024%

    No Known Activations