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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14548
    Prev
    Next
    INDEX
    Explanations

    references to specific ages

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
    ↵↵
    -0.51
     ModelExpression
    -0.50
     '\\;'
    -0.50
    ,
    -0.48
     старости
    -0.47
     (
    -0.46
    tmpl
    -0.45
     un
    -0.45
    .
    -0.45
     of
    -0.44
    POSITIVE LOGITS
     Anſ
    0.83
     Theſe
    0.82
    ?";
    0.80
    ".
    
    0.76
     дописавши
    0.76
     sèche
    0.75
     Jefus
    0.73
    )*/
    0.72
    ?");
    0.72
    )».
    0.71
    Activations Density 0.016%

    No Known Activations