© 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. 20471
    Prev
    Next
    INDEX
    Explanations

    references to coal and its related context

    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
    Negative Logits
    MethodManager
    -0.82
     Draht
    -0.69
     circles
    -0.69
     EconPapers
    -0.68
     Aras
    -0.66
    GeneratedMessage
    -0.64
     Saran
    -0.63
    
    -0.63
    cheibe
    -0.62
    न्द
    -0.61
    POSITIVE LOGITS
     coal
    1.66
    Coal
    1.52
     Coal
    1.51
     COAL
    1.36
    coal
    1.35
     coals
    1.31
    COAL
    1.13
     Anth
    0.92
     anth
    0.92
     carbón
    0.88
    Activations Density 0.003%

    No Known Activations