© 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. 3-RES-MATRYOSHKA-DC
    7. 1754
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings involving juries

    oai_token-act-pair · gemini-2.0-flash
    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
     Hartman
    -0.61
    Hochspringen
    -0.57
     Clair
    -0.57
     board
    -0.55
     J
    -0.54
    Transparent
    -0.53
     Council
    -0.53
     Transparent
    -0.52
    enskap
    -0.51
     I
    -0.50
    POSITIVE LOGITS
     jury
    2.88
     Jury
    2.45
    Jury
    2.36
     juries
    2.36
    jury
    2.23
     jurors
    1.80
     juror
    1.48
     jurado
    1.25
     Jur
    1.12
    Jur
    1.03
    Activations Density 0.047%

    No Known Activations