© 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. 12073
    Prev
    Next
    INDEX
    Explanations

    references to legal procedural actions and rules

    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
     Kingsley
    -0.65
    Rüyada
    -0.64
    }}{(
    -0.63
    <thead>
    -0.62
    rament
    -0.62
     Kear
    -0.62
     conseils
    -0.61
     NKC
    -0.61
     Haji
    -0.60
    "])){
    -0.60
    POSITIVE LOGITS
    AxisAlignment
    0.67
     مشين
    0.54
    ècie
    0.54
     layui
    0.51
    mű
    0.50
    NUMX
    0.48
     aDecoder
    0.48
    omitempty
    0.46
    couvrez
    0.45
    ergies
    0.45
    Activations Density 0.110%

    No Known Activations