© 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. 97769
    Prev
    Next
    INDEX
    Explanations

    AFP

    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
    AddTagHelper
    -0.94
     kasarigan
    -0.86
     AssemblyProduct
    -0.82
    setupUi
    -0.80
    TagHelpers
    -0.77
     propOrder
    -0.77
     Italijanski
    -0.76
    ChildScrollView
    -0.75
     المعيارى
    -0.73
    InitVars
    -0.73
    POSITIVE LOGITS
    州市
    0.49
     lovel
    0.45
     Ju
    0.43
    &&
    0.42
    endo
    0.41
     Church
    0.41
    arder
    0.41
     zapo
    0.41
    ↵↵
    0.40
     Bo
    0.40
    Activations Density 1.590%

    No Known Activations