© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    references to lethal actions or deaths

    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
    kill
    -0.86
     Kill
    -0.82
    Kill
    -0.81
     kill
    -0.71
     killing
    -0.68
    killing
    -0.67
     KILL
    -0.67
     Killing
    -0.65
     killer
    -0.63
    KILL
    -0.62
    POSITIVE LOGITS
     killed
    1.71
     Killed
    1.49
     murdered
    1.25
    killed
    1.20
    Killed
    1.01
     slain
    0.97
     tué
    0.95
     assassinated
    0.79
     погиб
    0.71
    unknownFields
    0.70
    Activations Density 0.004%

    No Known Activations