© 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. 30907
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their quantifiable effects

    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
     bezig
    -0.56
     "")
    -0.56
     فريبيس
    -0.54
     يتيمه
    -0.54
    لينا
    -0.52
     становника
    -0.52
    ")))
    -0.51
     juniors
    -0.51
    Diweddarwch
    -0.51
     '/',
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    AccessLevel
    0.57
     chè
    0.57
     aDecoder
    0.56
    edith
    0.55
    ✨:
    0.55
    GeneratedCode
    0.54
    *>(
    0.52
    endwhile
    0.52
    لاف
    0.51
    Activations Density 0.009%

    No Known Activations