© 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. 6555
    Prev
    Next
    INDEX
    Explanations

    references to legal procedures and principles related to evidence, admissibility, and court rulings

    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
    Хьажоргаш
    -0.63
    lück
    -0.59
    ména
    -0.57
    씩
    -0.55
     nobody
    -0.54
    “……”
    -0.53
     springfox
    -0.53
    代わりに
    -0.53
     officiellement
    -0.53
     wireType
    -0.53
    POSITIVE LOGITS
    findpost
    0.85
    </thead>
    0.63
     ProtoMessage
    0.58
    </tfoot>
    0.57
     hervor
    0.57
     ratify
    0.57
     himo
    0.56
     خارجية
    0.56
    OGND
    0.56
    Voci
    0.55
    Activations Density 1.008%

    No Known Activations