© 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. 11850
    Prev
    Next
    INDEX
    Explanations

    terms associated with fatal consequences or outcomes

    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
    Royce
    -0.74
     InputDecoration
    -0.69
    AnchorStyles
    -0.68
     переписи
    -0.65
     Prou
    -0.63
     برانيه
    -0.61
     Archa
    -0.61
    nsito
    -0.60
     Ruck
    -0.60
     getchar
    -0.60
    POSITIVE LOGITS
     fatal
    1.09
    Fatal
    1.09
    fatal
    1.09
     Fatal
    1.08
     Lethal
    1.04
     lethal
    0.98
    Deadly
    0.91
    jsonwebtoken
    0.90
     Deadly
    0.90
    lethal
    0.87
    Activations Density 0.003%

    No Known Activations