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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14171
    Prev
    Next
    INDEX
    Explanations

    java import statements

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    :
    -0.66
     
    -0.66
    ,
    -0.63
      
    -0.62
    ↵
    -0.61
     A
    -0.58
    '
    -0.55
    ↵↵
    -0.54
     No
    -0.54
     a
    -0.54
    POSITIVE LOGITS
     ModelExpression
    1.57
     مشين
    1.54
    endphp
    1.47
    LookAnd
    1.45
     betweenstory
    1.42
    expandindo
    1.41
    AddTagHelper
    1.35
     ProtoMessage
    1.35
    IntoConstraints
    1.33
    RenderAtEndOf
    1.33
    Activations Density 0.704%

    No Known Activations