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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14272
    Prev
    Next
    INDEX
    Explanations

    the words "dry" and "wet", especially together

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     dry
    -2.98
    dry
    -2.72
    Dry
    -2.61
     Dry
    -2.61
     DRY
    -2.17
    DRY
    -1.98
     dries
    -1.77
     dryness
    -1.73
     trock
    -1.64
     drier
    -1.64
    POSITIVE LOGITS
    CodeAnalysis
    0.52
     useRef
    0.47
     PhpStorm
    0.47
     plotly
    0.45
    gelijk
    0.44
    ResponseWriter
    0.44
    disambiguation
    0.44
    stdarg
    0.42
    PositiveButton
    0.42
    ponses
    0.42
    Activations Density 0.922%

    No Known Activations