© 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. 951
    Prev
    Next
    INDEX
    Explanations

    dera

    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
     requesting
    -0.83
     needing
    -0.80
     messing
    -0.76
     concentrating
    -0.75
     looking
    -0.74
     responding
    -0.73
     showing
    -0.71
     answering
    -0.71
     seeking
    -0.71
     killing
    -0.71
    POSITIVE LOGITS
    脚注の使い方
    0.92
     NSCoder
    0.71
    RetentionPolicy
    0.67
     وتسجيلات
    0.61
    RenderAtEndOf
    0.59
    ViewFeatures
    0.54
    MarshalTo
    0.52
     diputados
    0.50
    }:${
    0.49
     فريبيس
    0.49
    Activations Density 0.023%

    No Known Activations