© 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. 95047
    Prev
    Next
    INDEX
    Explanations

    I

    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
    phus
    -0.44
    '
    -0.42
    拓
    -0.42
     kre
    -0.39
     ad
    -0.38
     bet
    -0.38
    Alder
    -0.38
    ív
    -0.37
    essentiel
    -0.37
    LAYOUT
    -0.36
    POSITIVE LOGITS
     تضيفلها
    0.97
     ویکی‌پدی
    0.91
     kasarigan
    0.88
     CreateTagHelper
    0.87
     للمعارف
    0.86
    وفاته
    0.78
    GEBURTS
    0.74
     насељу
    0.74
     समीक्षक
    0.72
     Titanic
    0.71
    Activations Density 0.021%

    No Known Activations