© 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. 4359
    Prev
    Next
    INDEX
    Explanations

    references to legal convictions

    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
     ModelExpression
    -0.81
     autorytatywna
    -0.60
    日语
    -0.56
    ()?.
    -0.56
    Cons
    -0.54
    новниш
    -0.54
    MENAFN
    -0.52
     typelib
    -0.52
    WireFormatLite
    -0.50
    Rujuakan
    -0.49
    POSITIVE LOGITS
     conviction
    2.59
     convictions
    2.03
     convic
    1.45
     Conv
    1.35
     CONV
    1.29
    conv
    1.21
    Conv
    1.11
     convicted
    0.97
     convinced
    0.94
    CONV
    0.91
    Activations Density 0.018%

    No Known Activations