© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    signed

    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
     pulumi
    -0.71
     NSCoder
    -0.68
    RunWith
    -0.59
    Referencie
    -0.58
     AppModule
    -0.58
    AccessorTable
    -0.57
    原始内容存档于
    -0.57
    "])
    -0.57
     defaultstate
    -0.57
    AutoScale
    -0.56
    POSITIVE LOGITS
    ographed
    0.56
    asional
    0.54
     versi
    0.54
    WebElementEntity
    0.50
     (!_
    0.48
     essais
    0.48
     Decorative
    0.48
     Presumably
    0.47
     Variante
    0.47
     coloured
    0.47
    Activations Density 0.124%

    No Known Activations