Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11157
    Prev
    Next
    INDEX
    Explanations

    mentions of election results, sports results, or competitions in general

    oai_token-act-pair · gemini-2.0-flash

    words related to performance or results

    np_token-act-pair-logits · gpt-4o-mini

    results/outcomes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CopyWith
    -0.57
     AssemblyCulture
    -0.57
    Véxase
    -0.52
    addCriterion
    -0.51
    arraycopy
    -0.50
    ImageContext
    -0.50
     ModelExpression
    -0.49
    queryInterface
    -0.47
    basicConfig
    -0.46
     /\.
    -0.46
    POSITIVE LOGITS
     performance
    0.94
    performance
    0.79
     haul
    0.74
     result
    0.73
     outcome
    0.73
     finish
    0.71
     performances
    0.71
     showing
    0.71
     Performance
    0.70
     accomplishment
    0.70
    Activations Density 2.252%

    No Known Activations