© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5682
    Prev
    Next
    INDEX
    Explanations

    instances of violent actions, specifically shootings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.85
     "}
    -0.74
    giaan
    -0.73
    ilever
    -0.72
    EventName
    -0.72
     Collapse
    -0.72
    DISTR
    -0.69
     Dacia
    -0.68
     hâte
    -0.68
     Decken
    -0.67
    POSITIVE LOGITS
     shots
    1.75
     shot
    1.70
     shoots
    1.66
    Shots
    1.63
     Shots
    1.60
     SHOT
    1.60
    shots
    1.56
     shoot
    1.55
     Shot
    1.55
    shot
    1.52
    Activations Density 0.047%

    No Known Activations