© 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. 1-CLT-HP
    7. 12990
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     Meksiku
    -0.58
     Pony
    -0.54
    osoba
    -0.53
     Welfare
    -0.52
     maux
    -0.51
     WELFARE
    -0.51
    pony
    -0.51
    Jeografia
    -0.51
    nī
    -0.50
    ystemet
    -0.49
    POSITIVE LOGITS
    出版年
    0.81
    ful
    0.81
    ed
    0.73
    ous
    0.72
    ChildScrollView
    0.70
    PYX
    0.69
    RenderAtEndOf
    0.61
    setVerticalGroup
    0.60
    ImageContext
    0.60
     intptr
    0.57
    Activations Density 0.015%

    No Known Activations