© 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. 14070
    Prev
    Next
    INDEX
    Explanations

    references to acts of violence or physical assault

    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
     RSSSF
    -0.63
    AndEndTag
    -0.60
     aérea
    -0.59
     reven
    -0.57
    Migrations
    -0.57
    ſelf
    -0.56
    --}}
    -0.56
     KML
    -0.56
    ](#
    -0.56
     Vedi
    -0.55
    POSITIVE LOGITS
     assault
    2.67
     Assault
    2.14
    Assault
    1.87
     assaults
    1.79
     assaulted
    1.69
     assaulting
    1.65
     asalto
    1.29
     assa
    0.79
    Халык
    0.66
     betweenstory
    0.65
    Activations Density 0.001%

    No Known Activations