© 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. 5196
    Prev
    Next
    INDEX
    Explanations

    references to the concept of death or dead bodies

    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
    spender
    -0.82
    suicide
    -0.71
    BeginContext
    -0.67
     suicide
    -0.67
     urbanization
    -0.66
     Thurston
    -0.65
     chofe
    -0.63
     death
    -0.63
     typelib
    -0.63
    death
    -0.62
    POSITIVE LOGITS
     dead
    3.73
     Dead
    3.38
    dead
    3.33
    Dead
    3.30
     DEAD
    2.97
    DEAD
    2.52
     мерт
    1.73
     muertos
    1.58
     muerto
    1.45
     muerta
    1.38
    Activations Density 0.017%

    No Known Activations