© 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. 1036
    Prev
    Next
    INDEX
    Explanations

    code/formulas/notations

    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
     AssemblyCulture
    -0.58
    insics
    -0.54
    InjectAttribute
    -0.54
    ItemBackground
    -0.52
    abestanden
    -0.52
    MessageOf
    -0.52
     onCreateView
    -0.52
    CompilerServices
    -0.51
    richTextPanel
    -0.50
    MENAFN
    -0.48
    POSITIVE LOGITS
    ,
    0.67
     and
    0.61
    hq
    0.52
    userAgent
    0.52
     with
    0.50
    -
    0.50
    PerformLayout
    0.49
    RenderAtEndOf
    0.47
     Lors
    0.47
     Menge
    0.47
    Activations Density 0.011%

    No Known Activations