© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92339
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ,
    -1.00
    <eos>
    -0.96
    :
    -0.65
    ↵↵
    -0.64
    ...
    -0.56
    ;
    -0.54
    '
    -0.54
    ier
    -0.53
     "
    -0.52
    ?
    -0.48
    POSITIVE LOGITS
     itſelf
    1.27
     myſelf
    1.22
     Efq
    1.20
     himſelf
    1.13
     Monfieur
    1.11
     Jefus
    1.09
     feroit
    1.09
     enfans
    1.07
     Theſe
    1.07
     pleaſure
    1.04
    Activations Density 0.967%

    No Known Activations