© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14763
    Prev
    Next
    INDEX
    Explanations

    terms related to violence, injury, and legal consequences associated with bodily harm

    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
    InvalidProtocol
    -0.63
    — 
    -0.60
    nava
    -0.58
    }));
    -0.56
    "])){
    -0.56
    dym
    -0.55
    )$_
    -0.54
    }))
    -0.54
     bậc
    -0.53
    bilt
    -0.52
    POSITIVE LOGITS
    Alpes
    0.57
     humaine
    0.56
     MainAxisSize
    0.54
    ########.
    0.53
     telt
    0.53
     peup
    0.53
     onCreateView
    0.52
    ietal
    0.52
    stalline
    0.52
     carnal
    0.52
    Activations Density 0.017%

    No Known Activations