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. 16309
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are verbs related to the simple past tense form or the past participle form

    oai_token-act-pair · gemini-2.0-flash

    was

    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
     was
    -0.79
     would
    -0.67
     became
    -0.66
    would
    -0.65
     wasn
    -0.65
    wasn
    -0.62
    became
    -0.62
     were
    -0.62
     could
    -0.61
    ходил
    -0.58
    POSITIVE LOGITS
     للاسماء
    0.89
     AssemblyTitle
    0.83
    yntaxException
    0.78
    Билгалдахарш
    0.75
     ReactDOM
    0.72
    posedge
    0.72
    ControllerAdvice
    0.71
    oa̍t
    0.70
     nahilalakip
    0.70
     незавершена
    0.69
    Activations Density 2.573%

    No Known Activations