© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1047
    Prev
    Next
    INDEX
    Explanations

    references to high-ranking judicial authorities, specifically "Superior" courts and related judicial terms

    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
    nastics
    -0.61
     purposeful
    -0.60
     purposefully
    -0.59
     Buxton
    -0.56
     innoc
    -0.55
    ⁂
    -0.55
     ods
    -0.54
     forward
    -0.54
     deliberate
    -0.52
     commercially
    -0.50
    POSITIVE LOGITS
     Superior
    2.70
    Superior
    2.66
     superior
    2.63
    superior
    2.63
     SUPERIOR
    2.42
     Supreme
    2.25
     supreme
    2.11
     senior
    2.09
    Supreme
    2.03
    senior
    1.98
    Activations Density 0.583%

    No Known Activations