© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    mentions of jurisdiction

    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
    Datuak
    -0.72
    publicain
    -0.65
    참고
    -0.58
    )];
    -0.58
    =?";
    -0.58
     objectMapper
    -0.58
     kaynağından
    -0.57
    +};
    -0.57
    يميديا
    -0.57
     StringField
    -0.57
    POSITIVE LOGITS
     jurisdiction
    3.11
     Jurisdiction
    2.78
     JURIS
    2.28
    juris
    2.14
     jurisdictions
    2.02
     jurisdic
    1.99
    Juris
    1.98
     jurisdictional
    1.79
     Juris
    1.52
     juris
    1.19
    Activations Density 0.007%

    No Known Activations