© 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. 95027
    Prev
    Next
    INDEX
    Explanations

    decisions

    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
    ⓧ
    -0.99
    BagConstraints
    -0.71
    GEBURTSDATUM
    -0.66
    ViewImports
    -0.60
    oredCriteria
    -0.58
     NSCoder
    -0.57
    InjectAttribute
    -0.56
    SpringBootTest
    -0.56
     Infórmanos
    -0.55
    ClientRect
    -0.55
    POSITIVE LOGITS
    oléon
    0.52
    NewValue
    0.50
    mallows
    0.49
    roffene
    0.47
    бири
    0.47
    ersachsen
    0.47
    Decision
    0.47
    人人
    0.46
    خفض
    0.46
    Schon
    0.46
    Activations Density 0.002%

    No Known Activations