© 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. 2-RES-MATRYOSHKA-DC
    7. 2987
    Prev
    Next
    INDEX
    Explanations

    references to the death penalty or executions

    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
     killed
    -0.86
     slain
    -0.85
     murdered
    -0.84
     kills
    -0.81
    killed
    -0.80
     kill
    -0.79
     killings
    -0.77
     massac
    -0.77
     dead
    -0.76
     murdering
    -0.74
    POSITIVE LOGITS
     death
    2.31
     Death
    2.25
    Death
    2.09
    death
    2.08
     DEATH
    1.95
    DEATH
    1.71
     muerte
    1.20
     смерти
    1.05
     morte
    0.99
     смерть
    0.96
    Activations Density 0.016%

    No Known Activations