© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13909
    Prev
    Next
    INDEX
    Explanations

    statements about legal prohibitions

    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
    addContainerGap
    -0.76
    mappedBy
    -0.75
    complexContent
    -0.73
    Witam
    -0.68
    NewUrlParser
    -0.68
    fchen
    -0.68
    )^(
    -0.67
    )";
    -0.67
    Zacks
    -0.64
    mybatisplus
    -0.64
    POSITIVE LOGITS
     prohibited
    2.14
     forbidden
    1.29
    hibited
    1.21
    forbidden
    1.02
    Forbidden
    0.93
     banned
    0.91
     Forbidden
    0.82
     prohibido
    0.60
     barred
    0.58
     verboten
    0.55
    Activations Density 0.003%

    No Known Activations