© 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. 1-CLT-HP
    7. 336
    Prev
    Next
    INDEX
    Explanations

    ber

    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
     AssemblyCulture
    -0.77
    InstrumentedTest
    -0.76
    AntiForgeryToken
    -0.76
    таратура
    -0.73
    DockStyle
    -0.69
    AnimationsModule
    -0.69
    ISupport
    -0.68
     transfieras
    -0.67
     kasarigan
    -0.66
    InjectAttribute
    -0.66
    POSITIVE LOGITS
    ighton
    0.49
     taget
    0.47
    weis
    0.47
     }}}{
    0.45
     slik
    0.44
    setzer
    0.43
    "]();
    0.43
    ofman
    0.42
    复制代码
    0.41
    Tikang
    0.41
    Activations Density 0.028%

    No Known Activations