© 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. 39993
    Prev
    Next
    INDEX
    Explanations

    quick ultimate

    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
     quick
    -0.96
    quick
    -0.94
    sizeCache
    -0.85
    MessageOf
    -0.84
    RenderAtEndOf
    -0.83
    BeginContext
    -0.82
    AndEndTag
    -0.81
     instant
    -0.81
     disponibilités
    -0.80
     kasarigan
    -0.79
    POSITIVE LOGITS
    ening
    0.70
     of
    0.55
    aneous
    0.55
     to
    0.54
    ary
    0.50
    ative
    0.49
    іга
    0.46
    ulate
    0.45
    forward
    0.45
    sive
    0.44
    Activations Density 0.170%

    No Known Activations