© 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. 0-RES-MATRYOSHKA-DC
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    references to legal authority or 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
     scope
    -1.59
     authority
    -1.41
    scope
    -1.34
     Scope
    -1.33
     Authority
    -1.32
    Scope
    -1.22
    Authority
    -1.20
    authority
    -1.18
     AUTHORITY
    -1.16
     scopes
    -1.11
    POSITIVE LOGITS
     jurisdiction
    1.80
     Jurisdiction
    1.40
     jurisdictions
    1.10
     JURIS
    1.05
    Geplaatst
    0.85
     jurisdic
    0.84
     '{@
    0.76
    -------------</
    0.73
    abestanden
    0.69
    RegistryLite
    0.68
    Activations Density 0.003%

    No Known Activations