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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16176
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one"

    oai_token-act-pair · gemini-2.0-flash

    one

    np_token-act-pair-logits · gemini-2.0-flash

    One

    np_max-act-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
     provi
    -0.46
    argout
    -0.45
     hoo
    -0.44
    caccio
    -0.44
    parseColor
    -0.43
    deoxy
    -0.42
     format
    -0.42
    azol
    -0.40
    Explicación
    -0.40
    DataSnapshot
    -0.40
    POSITIVE LOGITS
    Datuak
    0.85
    WireFormatLite
    0.79
    setVerticalGroup
    0.77
    richTextPanel
    0.73
    RenderAtEndOf
    0.69
    DockStyle
    0.66
     resourceCulture
    0.64
    الحياه
    0.63
    GEBURTS
    0.62
    ंदीखरीदारी
    0.60
    Activations Density 0.371%

    No Known Activations