© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    emphasis

    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
     reference
    -2.11
    reference
    -2.02
     Reference
    -1.77
    Reference
    -1.77
     references
    -1.53
    REFERENCE
    -1.53
     référence
    -1.51
     REFERENCE
    -1.50
     referencia
    -1.41
    references
    -1.41
    POSITIVE LOGITS
     to
    0.69
     on
    0.63
     in
    0.58
     for
    0.57
     and
    0.54
    ,
    0.52
    ;
    0.48
     put
    0.47
     from
    0.47
     into
    0.46
    Activations Density 0.192%

    No Known Activations