© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    references to firearm discharges or gunshot 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
     weapon
    -0.98
     weapons
    -0.95
     Weapons
    -0.82
    weapons
    -0.81
    ArgsConstructor
    -0.81
    weapon
    -0.81
    Weapons
    -0.74
     knife
    -0.73
     Weapon
    -0.73
    Weapon
    -0.72
    POSITIVE LOGITS
     shot
    3.44
     Shot
    3.05
    shot
    2.94
    Shot
    2.91
     SHOT
    2.75
     shots
    2.72
     Shots
    2.47
    shots
    2.45
    SHOT
    2.39
    Shots
    2.25
    Activations Density 0.014%

    No Known Activations