© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42705
    Prev
    Next
    INDEX
    Explanations

    hyphens and parentheses

    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
    -.
    -0.99
    -'
    -0.97
    -)
    -0.95
    -"
    -0.95
    -,
    -0.88
    nets
    -0.84
    -]
    -0.84
    -!
    -0.79
    -(
    -0.76
    -#
    -0.73
    POSITIVE LOGITS
    :],
    0.71
    setVerticalGroup
    0.70
    \
    0.69
    .
    0.63
    ]='\
    0.63
    znym
    0.62
    chowa
    0.61
    (
    0.61
    "
    0.61
    dited
    0.60
    Activations Density 1.454%

    No Known Activations