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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1208
    Prev
    Next
    INDEX
    Explanations

    Raw text/document content

    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
    ValueStyle
    -0.66
     dévelo
    -0.58
     Efq
    -0.57
     whoſe
    -0.57
     rémun
    -0.56
     Towels
    -0.56
    gjenge
    -0.56
    InputBorder
    -0.56
     disappointed
    -0.56
     autorité
    -0.55
    POSITIVE LOGITS
     through
    0.60
     on
    0.59
     in
    0.55
     as
    0.52
    tvguidetime
    0.51
     from
    0.47
    annica
    0.47
     by
    0.47
    pyx
    0.46
     with
    0.44
    Activations Density 0.003%

    No Known Activations