© 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. 1-CLT-HP
    7. 12082
    Prev
    Next
    INDEX
    Explanations

    pooling

    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
    ConstraintMaker
    -0.78
    RenderAtEndOf
    -0.72
     camps
    -0.66
    #+#
    -0.65
    enumi
    -0.63
    aarrggbb
    -0.63
     myſelf
    -0.62
     становника
    -0.61
    WriteBarrier
    -0.61
    ^(@)
    -0.60
    POSITIVE LOGITS
    nun
    0.48
    in
    0.45
    n
    0.43
    native
    0.42
    por
    0.42
    extra
    0.42
    pas
    0.42
    허
    0.41
     INSEE
    0.41
    trans
    0.40
    Activations Density 0.037%

    No Known Activations