© 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. 7026
    Prev
    Next
    INDEX
    Explanations

    references to committing suicide or homicide

    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
     promise
    -0.99
     promising
    -0.90
    promise
    -0.88
     promises
    -0.86
     Promise
    -0.85
    promises
    -0.80
     promised
    -0.80
    Promise
    -0.77
     promessa
    -0.75
     Promises
    -0.71
    POSITIVE LOGITS
     commit
    3.36
     committed
    3.06
    commit
    2.98
     Commit
    2.95
     COMMIT
    2.92
     committing
    2.84
     commits
    2.84
    Commit
    2.70
    committed
    2.70
     Committed
    2.63
    Activations Density 0.021%

    No Known Activations