© 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. 2-RES-MATRYOSHKA-DC
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    mentions related to legal parties such as plaintiffs or appellants

    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
     plaintiffs
    -0.66
     plaintiff
    -0.60
     petitioners
    -0.56
     prayed
    -0.54
     defendants
    -0.53
     appellant
    -0.51
    Scrollable
    -0.50
     petitioner
    -0.50
    dataProvider
    -0.46
    Enlaces
    -0.46
    POSITIVE LOGITS
     Defendant
    1.57
    Plaintiff
    1.39
     Plaintiff
    1.32
     Defendants
    1.30
    Defendant
    1.16
     Plaintiffs
    1.09
     Appellee
    0.99
    Appellee
    0.79
     Appellant
    0.77
     Appellants
    0.77
    Activations Density 0.033%

    No Known Activations