© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    watch

    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
     watch
    -1.17
     observe
    -0.93
     WATCH
    -0.91
     Watch
    -0.90
    Watch
    -0.83
    watch
    -0.81
    WATCH
    -0.81
     watched
    -0.80
    observation
    -0.80
     Observe
    -0.78
    POSITIVE LOGITS
    igay
    0.63
    MigrationBuilder
    0.60
    ystis
    0.57
    StreetMap
    0.54
     <=",
    0.51
     trus
    0.50
     rectal
    0.49
    webElementXpaths
    0.48
    脚注の使い方
    0.48
     shale
    0.47
    Activations Density 0.193%

    No Known Activations