© 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. 4-CLT-HP
    7. 630
    Prev
    Next
    INDEX
    Explanations

    excerpts

    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
    
    -0.46
    #![
    -0.43
    GEBURTS
    -0.43
     Toy
    -0.42
     IOError
    -0.42
    agosto
    -0.40
    Toy
    -0.39
    matters
    -0.38
     usah
    -0.37
    ின
    -0.37
    POSITIVE LOGITS
     surla
    1.03
    LookAnd
    0.93
    EndGlobalSection
    0.93
    setVerticalGroup
    0.92
     صوتيه
    0.88
     saites
    0.86
    ArrowToggle
    0.85
     للمعارف
    0.85
     ModelExpression
    0.82
    ########.
    0.82
    Activations Density 0.003%

    No Known Activations