© 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. 6-RES-MATRYOSHKA-DC
    7. 21
    Prev
    Next
    INDEX
    Explanations

    citations of legal cases with volume/page numbers and court identifiers.

    oai_token-act-pair · gemini-2.0-flash
    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
    aarrggbb
    -0.81
    RTLD
    -0.70
    bewerken
    -0.61
     <=",
    -0.59
    Бахар
    -0.56
     ModelExpression
    -0.56
    ->__
    -0.55
    Personensuche
    -0.55
     himo
    -0.54
     StringTokenizer
    -0.54
    POSITIVE LOGITS
    rungsseite
    0.66
     الحره
    0.59
     שוליים
    0.56
    mso
    0.56
     viewType
    0.54
    reamble
    0.54
     reh
    0.53
    ówczas
    0.52
     voulons
    0.49
    rxjs
    0.47
    Activations Density 5.207%

    No Known Activations