© 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. 1-CLT-HP
    7. 14956
    Prev
    Next
    INDEX
    Explanations

    voter

    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
     voter
    -1.32
     Voter
    -1.13
    __*/
    -1.02
    Voter
    -0.93
    voter
    -0.88
    RectangleBorder
    -0.85
    曖昧さ回避
    -0.82
    
    -0.76
    oa̍t
    -0.75
     Voters
    -0.73
    POSITIVE LOGITS
    '
    0.56
    ’
    0.52
     rangs
    0.47
     here
    0.46
    portar
    0.45
     
    0.43
    matite
    0.43
     nghi
    0.42
    TableData
    0.41
    ever
    0.41
    Activations Density 0.039%

    No Known Activations