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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 2126
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or someone dealing with anxiety

    oai_token-act-pair · gemini-2.0-flash

    Advice and suggestions

    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
    parsedMessage
    -0.90
    ReusableCell
    -0.80
    expandindo
    -0.78
     nahilalakip
    -0.77
     дописавши
    -0.75
    RegressionTest
    -0.72
     beginnetje
    -0.70
    AccessorTable
    -0.69
    MLLoader
    -0.68
     виправивши
    -0.66
    POSITIVE LOGITS
    taw
    0.48
    .’”
    0.47
    '")
    0.46
    oldi
    0.46
     reference
    0.45
    ,’”
    0.45
    zzar
    0.43
    reference
    0.42
    INCREF
    0.41
    AccessFile
    0.41
    Activations Density 1.149%

    No Known Activations