© 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. 5523
    Prev
    Next
    INDEX
    Explanations

    mentions of violent crimes, specifically 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
    annica
    -0.62
    存于互联网档案馆
    -0.60
    кер
    -0.59
    Webb
    -0.58
    trise
    -0.57
     Tér
    -0.57
     conci
    -0.56
     sprá
    -0.54
    ])]
    -0.54
     Coward
    -0.54
    POSITIVE LOGITS
     assault
    2.45
     Assault
    2.30
    Assault
    1.91
     assaulted
    1.79
     assaults
    1.74
     assaulting
    1.66
     asalto
    1.13
     assa
    0.99
    principalColumn
    0.73
    aults
    0.72
    Activations Density 0.002%

    No Known Activations