© 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. 11615
    Prev
    Next
    INDEX
    Explanations

    references to severe or capital punishment, including laws, cases, or discussions about the death penalty and related legal practices

    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
     penalty
    -1.15
     penal
    -1.07
    penalty
    -0.97
     Penalty
    -0.95
     الرياضيه
    -0.90
     penalties
    -0.87
     censiti
    -0.85
     penalized
    -0.82
    Penalty
    -0.75
     ویکی‌پدی
    -0.69
    POSITIVE LOGITS
     punishment
    2.11
     Punishment
    1.54
     punishments
    1.20
     castigo
    1.03
    IGraphics
    0.61
     punish
    0.59
    Tikang
    0.58
     picioare
    0.57
     punished
    0.56
     hukuman
    0.54
    Activations Density 0.002%

    No Known Activations