© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40499
    Prev
    Next
    INDEX
    Explanations

    heroes

    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
     hierarchy
    -0.78
    Hierarchy
    -0.67
     Hierarchy
    -0.67
    hierarchy
    -0.59
     marrone
    -0.57
     Severity
    -0.55
     Técnico
    -0.54
     Theſe
    -0.54
     flotante
    -0.53
     azzurro
    -0.53
    POSITIVE LOGITS
    EndGlobalSection
    0.72
    SharedDtor
    0.67
    ViewImports
    0.62
    migrationBuilder
    0.61
    PRNewswire
    0.61
     nahilalakip
    0.59
    IUrlHelper
    0.58
    WireFormatLite
    0.57
    rrggbb
    0.57
     surla
    0.56
    Activations Density 0.145%

    No Known Activations