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. 16162
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and numerical data

    oai_token-act-pair · gemini-2.0-flash

    statistical analysis

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

    using

    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
    nbt
    -0.44
     Malle
    -0.43
     viewType
    -0.43
    alt
    -0.42
     never
    -0.41
     bodyParser
    -0.40
     mai
    -0.40
     sun
    -0.40
    ď
    -0.40
    Eres
    -0.39
    POSITIVE LOGITS
    LookAnd
    0.83
    complexContent
    0.83
     otomatig
    0.76
     myſelf
    0.74
    matchCondition
    0.74
    الحياه
    0.73
    InjectAttribute
    0.72
    oredCriteria
    0.72
     estekak
    0.71
    awtextra
    0.71
    Activations Density 4.538%

    No Known Activations