© 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. 25372
    Prev
    Next
    INDEX
    Explanations

    significant indicators of medical conditions

    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
     >=",
    -0.63
    DoubleQuotes
    -0.62
     Nude
    -0.59
    shund
    -0.58
    JAMIN
    -0.57
     Lest
    -0.57
    ingale
    -0.57
     Baran
    -0.57
    脚注の使い方
    -0.57
     nara
    -0.56
    POSITIVE LOGITS
    RegressionTest
    0.72
    ंदीखरीदारी
    0.66
    Personendaten
    0.54
    providedIn
    0.51
    Referències
    0.48
     BeautifulSoup
    0.47
     okuyayım
    0.47
    Šaltiniai
    0.46
    Rüyada
    0.45
    Bism
    0.45
    Activations Density 0.021%

    No Known Activations