© 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. 1242
    Prev
    Next
    INDEX
    Explanations

    events and news

    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
    time
    -0.85
    point
    -0.77
    ups
    -0.73
    book
    -0.71
    work
    -0.69
    lines
    -0.67
    list
    -0.67
    fold
    -0.66
     (
    -0.66
    k
    -0.66
    POSITIVE LOGITS
     myſelf
    1.16
     Jefus
    1.14
     Majefty
    1.14
     Theſe
    1.10
     Anſ
    1.09
     ſeveral
    1.09
     pleaſure
    1.09
     ſever
    1.08
     purpoſe
    1.08
     himſelf
    1.05
    Activations Density 1.483%

    No Known Activations