© 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. 1-RES-MATRYOSHKA-DC
    7. 584
    Prev
    Next
    INDEX
    Explanations

    references to violent actions, specifically attacks, assaults, or related violent incidents

    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
     Zephyr
    -0.51
     unsatisfactory
    -0.47
    ˾
    -0.46
     restrictive
    -0.45
    sko
    -0.44
     manca
    -0.44
    저
    -0.43
     ulei
    -0.43
     ineligible
    -0.43
    cupertino
    -0.43
    POSITIVE LOGITS
     attack
    3.19
     Attack
    2.91
     attacks
    2.88
    attack
    2.83
     ATTACK
    2.73
     attacked
    2.66
    Attack
    2.64
     attacking
    2.64
     Attacks
    2.64
    Attacks
    2.48
    Activations Density 0.815%

    No Known Activations