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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16339
    Prev
    Next
    INDEX
    Explanations

    code snippets and HTML tags/attributes

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    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
    AndEndTag
    -0.71
    MemoryWarning
    -0.65
    AddTagHelper
    -0.63
    StoryboardSegue
    -0.63
    참고
    -0.62
    TagMode
    -0.62
    enterOuterAlt
    -0.60
     Roskov
    -0.59
    %");
    -0.56
    Autoritní
    -0.56
    POSITIVE LOGITS
    íncia
    0.56
     Relation
    0.52
     relations
    0.51
     Dmit
    0.50
    отно
    0.50
     Relations
    0.49
    FieldBuilder
    0.48
     čin
    0.47
     Doubles
    0.47
     AttributeSet
    0.47
    Activations Density 1.369%

    No Known Activations