© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1322
    Prev
    Next
    INDEX
    Explanations

    references to judges or judicial figures

    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
    Negative Logits
     ویکی‌پدی
    -0.54
    Parcelize
    -0.49
    osex
    -0.49
    TypedDataSet
    -0.48
     <<<<<<<<<<<<<<
    -0.48
     consolidated
    -0.47
     declaración
    -0.47
     folgt
    -0.47
    Screen
    -0.46
    Попис
    -0.46
    POSITIVE LOGITS
     judge
    4.25
     Judge
    4.22
    Judge
    4.03
    judge
    3.69
     JUDGE
    3.67
     judges
    3.42
     Judges
    3.36
    JUDGE
    3.03
    Judges
    2.89
     judged
    2.55
    Activations Density 0.074%

    No Known Activations