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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10193
    Prev
    Next
    INDEX
    Explanations

    the first syllable of the word "money" or days of the week starting with the letters "Mon"

    oai_token-act-pair · gemini-2.0-flash

    mon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
     nahilalakip
    -0.70
     warrant
    -0.50
     ویکی‌پدیای
    -0.49
     Audiodateien
    -0.47
     ویکی‌پدیا
    -0.46
    extAlignment
    -0.45
    SharedCtor
    -0.45
     reger
    -0.45
    ems
    -0.44
     ice
    -0.44
    POSITIVE LOGITS
     StringTokenizer
    0.59
    sizeCache
    0.57
     MotionEvent
    0.57
     restTemplate
    0.56
    SerializedName
    0.52
    Kaynakça
    0.52
    AnimationsModule
    0.52
    urando
    0.49
    ufact
    0.48
     religieux
    0.48
    Activations Density 0.536%

    No Known Activations