© 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. 1-RES-MATRYOSHKA-DC
    7. 227
    Prev
    Next
    INDEX
    Explanations

    references to trust, agreements, and contracts

    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
    ../
    -0.54
    ьаж
    -0.54
    qtype
    -0.54
    migrationBuilder
    -0.53
    ERVE
    -0.52
    ortal
    -0.50
     Dep
    -0.49
    ictured
    -0.49
    mapsto
    -0.48
     Munt
    -0.48
    POSITIVE LOGITS
     agreement
    3.94
     agree
    3.67
     Agreement
    3.48
     agreed
    3.45
     Agree
    3.34
     agrees
    3.31
     agreeing
    3.31
    Agreement
    3.31
    agreement
    3.30
     agreements
    3.28
    Activations Density 1.620%

    No Known Activations