© 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. 20-CLT-HP
    7. 74514
    Prev
    Next
    INDEX
    Explanations

    my/our

    np_max-act-logits · 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
    脚注の使い方
    -1.05
    AnchorTagHelper
    -0.75
    RenderAtEndOf
    -0.74
     سكانية
    -0.71
    TypedDataSet
    -0.70
    AddTagHelper
    -0.69
    OGND
    -0.69
    awtextra
    -0.66
     EconPapers
    -0.66
    IsContent
    -0.64
    POSITIVE LOGITS
     humble
    0.73
     honest
    0.57
    humble
    0.56
     humilde
    0.55
     opp
    0.52
     option
    0.51
     respectful
    0.49
    honest
    0.46
     humb
    0.46
     understanding
    0.45
    Activations Density 0.002%

    No Known Activations