© 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. 9959
    Prev
    Next
    INDEX
    Explanations

    references to mathematical propositions or theorems

    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
     témoin
    -0.80
     témoins
    -0.78
    phazard
    -0.77
    adaptiveStyles
    -0.74
     urmă
    -0.73
     testigos
    -0.71
    Begriff
    -0.70
    öglichkeiten
    -0.70
    LError
    -0.70
    checklist
    -0.69
    POSITIVE LOGITS
     Proposition
    1.06
    Proposition
    0.95
     proposition
    0.82
     propositions
    0.82
    proposition
    0.68
    $)$
    0.65
     lenker
    0.64
    Allister
    0.63
     Cors
    0.62
    Duc
    0.61
    Activations Density 0.003%

    No Known Activations