© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5654
    Prev
    Next
    INDEX
    Explanations

    references to the exercise of judicial discretion in legal decision-making

    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
    ########.
    -1.23
     EconPapers
    -0.76
    Personendaten
    -0.76
    RenderAtEndOf
    -0.71
     Baillargeon
    -0.70
    GEBURTSDATUM
    -0.70
     Réponses
    -0.69
    elemField
    -0.68
    )++;
    -0.68
    UnsafeEnabled
    -0.68
    POSITIVE LOGITS
     discretion
    3.30
     Discretion
    2.20
    cretion
    1.70
     discretionary
    1.53
     Discre
    0.85
     discreet
    0.78
     discre
    0.75
    Discre
    0.69
     discernment
    0.69
    discre
    0.66
    Activations Density 0.005%

    No Known Activations