© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2166
    Prev
    Next
    INDEX
    Explanations

    summaries

    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
    DockStyle
    -1.14
    MigrationBuilder
    -0.96
    InvalidProtocol
    -0.93
    providedIn
    -0.92
     BoxFit
    -0.91
    UnsafeEnabled
    -0.90
    ConstraintMaker
    -0.90
    setVerticalGroup
    -0.90
    Geplaatst
    -0.87
    ViewFeatures
    -0.86
    POSITIVE LOGITS
     varies
    0.50
    vikle
    0.50
     vary
    0.47
     excellent
    0.47
     spans
    0.46
     compri
    0.45
     faceva
    0.45
     spanning
    0.44
     amazing
    0.43
     famous
    0.43
    Activations Density 0.004%

    No Known Activations