© 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. 42597
    Prev
    Next
    INDEX
    Explanations

    re

    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
    re
    -1.86
    Re
    -1.30
    RE
    -1.20
     Re
    -1.19
     re
    -1.06
     RE
    -0.93
    ré
    -0.77
     Rea
    -0.76
    reu
    -0.76
    res
    -0.73
    POSITIVE LOGITS
     working
    0.73
     Majefty
    0.72
     a
    0.71
     fueling
    0.71
     aiming
    0.70
     focusing
    0.69
     estekak
    0.68
     running
    0.68
     collaborating
    0.68
     consuming
    0.67
    Activations Density 0.120%

    No Known Activations