© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    Revolutionary

    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
     Lexington
    -1.52
    Lexington
    -1.27
     AssemblyProduct
    -0.78
    脚注の使い方
    -0.68
    CloseOperation
    -0.58
    :+:
    -0.57
     initComponents
    -0.56
    makeConstraints
    -0.56
    FieldBuilder
    -0.55
    IntoConstraints
    -0.55
    POSITIVE LOGITS
    sun
    0.56
    Demografie
    0.54
    INARY
    0.54
    ICAL
    0.52
    ly
    0.50
    ALLY
    0.50
     препратки
    0.49
    ViewFeatures
    0.47
    cookieParser
    0.47
    ians
    0.47
    Activations Density 0.014%

    No Known Activations