© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4649
    Prev
    Next
    INDEX
    Explanations

    instances of the word "illegal" in text

    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
    updateOne
    -0.57
    ituaries
    -0.54
    ennale
    -0.52
    发表于
    -0.51
    ArgsConstructor
    -0.50
     Cly
    -0.50
    ritation
    -0.49
    絮
    -0.49
    kud
    -0.49
     Macron
    -0.48
    POSITIVE LOGITS
     illegal
    3.02
    illegal
    2.77
     Illegal
    2.73
    Illegal
    2.48
     illegally
    2.20
     ilegal
    2.13
     illeg
    1.94
     unlawful
    1.74
     ileg
    1.55
     legality
    1.51
    Activations Density 0.006%

    No Known Activations