© 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. 20-CLT-HP
    7. 75987
    Prev
    Next
    INDEX
    Explanations

    Beginning of a text

    np_max-act-logits · 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
    Linking
    -0.54
    AsUp
    -0.53
    RTLR
    -0.52
    lizing
    -0.49
    IContainer
    -0.48
     Linking
    -0.48
    linking
    -0.46
    MigrationBuilder
    -0.45
    Ur
    -0.43
    maketitle
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.73
    IntoConstraints
    0.72
     NSCoder
    0.59
    homonymie
    0.57
     AttributeSet
    0.56
    
    0.54
     ribbons
    0.53
     okuyayım
    0.53
    bench
    0.53
    ViewImports
    0.52
    Activations Density 0.000%

    No Known Activations