© 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. 5205
    Prev
    Next
    INDEX
    Explanations

    instances where the court makes legal errors

    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
     tombé
    -0.53
     completion
    -0.52
    completion
    -0.51
    Submitted
    -0.50
     Completion
    -0.49
     completed
    -0.49
    kovsky
    -0.47
     Boswell
    -0.46
     Willard
    -0.46
     Provost
    -0.46
    POSITIVE LOGITS
     erred
    2.70
     Normdatei
    0.97
     errs
    0.94
    AddTagHelper
    0.92
    featureID
    0.80
    mybatisplus
    0.76
    WebElementEntity
    0.72
     chi̍t
    0.71
     חיצוניים
    0.70
    riezmann
    0.69
    Activations Density 0.003%

    No Known Activations