Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B
    3. 20-RES-MATRYOSHKA-DC
    4. 403
    Prev
    Next
    INDEX
    Explanations

    discourse markers and connective phrases, particularly those indicating contrast or elaboration

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     Chevron
    -0.56
     pinulongan
    -0.55
    CloseOperation
    -0.55
     McMahon
    -0.54
     onOptions
    -0.54
    chevron
    -0.54
     chevron
    -0.54
    cvt
    -0.52
     Wyn
    -0.51
     Вин
    -0.50
    POSITIVE LOGITS
    +;
    0.85
    ;;;
    0.79
     {;
    0.78
    ;;;;
    0.71
    ;";
    0.71
    (';
    0.69
     ;
    0.69
    %;
    0.69
    ;\\
    0.69
    .;
    0.68
    Activations Density 0.573%

    No Known Activations