© 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. 0-CLT-HP
    7. 97514
    Prev
    Next
    INDEX
    Explanations

    electronics and hardware

    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
     Integration
    -1.14
     integration
    -1.10
    Integration
    -1.03
    integration
    -0.96
     Integrations
    -0.82
     integración
    -0.78
     integrate
    -0.77
     integrating
    -0.77
    integrating
    -0.76
     integrations
    -0.75
    POSITIVE LOGITS
    GenerationType
    0.85
    ValueStyle
    0.81
    GraphicsUnit
    0.77
     سكانية
    0.72
     المعيارى
    0.72
    TintMode
    0.70
    хьтан
    0.68
    setVerticalGroup
    0.68
     censiti
    0.68
    UnitTesting
    0.67
    Activations Density 0.272%

    No Known Activations