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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16381
    Prev
    Next
    INDEX
    Explanations

    Unusual words

    np_max-act-logits · gemini-2.0-flash

    tokens referring to the season of fall

    oai_token-act-pair · gemini-2.0-flash

    fall

    np_token-act-pair-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     season
    -1.09
     seasonal
    -0.93
     Season
    -0.91
     SEASON
    -0.90
    season
    -0.88
     saison
    -0.87
    seasonal
    -0.85
    Season
    -0.84
     Seasonal
    -0.82
     mùa
    -0.82
    POSITIVE LOGITS
    Personensuche
    0.65
     Normdatei
    0.61
     CreateTagHelper
    0.58
    ⓧ
    0.55
    enskap
    0.52
    czywiście
    0.52
     groves
    0.52
     Firefly
    0.52
    WriteTagHelper
    0.50
     cloche
    0.50
    Activations Density 4.357%

    No Known Activations