© 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. 0-CLT-HP
    7. 97695
    Prev
    Next
    INDEX
    Explanations

    Proper nouns/codes

    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
     EconPapers
    -0.90
    ValueStyle
    -0.88
     للمعارف
    -0.87
     ComVisible
    -0.87
     FetchType
    -0.86
     propOrder
    -0.83
    styleType
    -0.82
    Personensuche
    -0.82
    ագրություններ
    -0.81
     Normdatei
    -0.81
    POSITIVE LOGITS
    '
    0.69
    ’
    0.63
    o
    0.57
     in
    0.57
    dic
    0.55
    ,
    0.55
    a
    0.54
    :
    0.53
     and
    0.53
    ing
    0.48
    Activations Density 0.072%

    No Known Activations