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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16257
    Prev
    Next
    INDEX
    Explanations

    descriptions of problems or errors

    oai_token-act-pair · gemini-2.0-flash

    Something is wrong

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     Hautes
    -0.47
     overeen
    -0.46
     Audiodateien
    -0.44
     especiais
    -0.44
    стоин
    -0.43
     vierge
    -0.42
    addCriterion
    -0.42
    enetrable
    -0.42
     isolé
    -0.42
     riuscito
    -0.41
    POSITIVE LOGITS
    \{\\
    0.79
    </tfoot>
    0.77
     FetchType
    0.76
    HomeAsUpEnabled
    0.72
     nonatomic
    0.71
    FirstResponder
    0.71
     BoxFit
    0.67
    prefixer
    0.66
    DoubleQuotes
    0.63
    reportWebVitals
    0.63
    Activations Density 0.580%

    No Known Activations