© 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. 4634
    Prev
    Next
    INDEX
    Explanations

    references to specific legal officials involved in court proceedings

    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
    glEnd
    -0.59
    usammen
    -0.55
    ‖
    -0.54
    chod
    -0.52
    منى
    -0.52
    MONGO
    -0.51
     Espan
    -0.50
    DECREF
    -0.50
    -------
    -0.47
    ‗
    -0.47
    POSITIVE LOGITS
     deputy
    3.00
     Deputy
    2.97
    Deputy
    2.89
    PUTY
    2.38
     Assistant
    2.09
    Assistant
    2.00
     assistant
    1.98
     deputies
    1.91
     ASSISTANT
    1.89
    assistant
    1.73
    Activations Density 0.034%

    No Known Activations