© 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. 93893
    Prev
    Next
    INDEX
    Explanations

    ahead

    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
     recommended
    -1.27
    recommended
    -1.17
     replacing
    -1.13
     replace
    -1.08
    Ahead
    -1.05
     ahead
    -1.04
    replacing
    -1.04
     AHEAD
    -1.00
    ahead
    -0.99
    Recommended
    -0.97
    POSITIVE LOGITS
    s
    0.72
    <eos>
    0.56
    ly
    0.56
     "
    0.50
     by
    0.48
    了
    0.48
    st
    0.48
     of
    0.47
     '
    0.47
     to
    0.45
    Activations Density 1.729%

    No Known Activations