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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1291
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    ,
    -1.23
    .
    -0.90
    -
    -0.82
     and
    -0.78
     or
    -0.68
    /
    -0.59
     in
    -0.59
    :
    -0.57
     as
    -0.56
    !
    -0.55
    POSITIVE LOGITS
    <bos>
    1.74
     myſelf
    1.41
     reaſon
    1.30
     theſe
    1.27
     himſelf
    1.27
     ſeveral
    1.25
     ainfi
    1.25
     itſelf
    1.25
     Theſe
    1.25
     leſs
    1.25
    Activations Density 0.216%

    No Known Activations