© 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. 24798
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to medical or technical proofs and concepts

    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
    rawDesc
    -0.54
    ](#
    -0.54
    andExpect
    -0.53
    tisseur
    -0.53
     sentenza
    -0.50
     permett
    -0.49
    isnan
    -0.49
    جراء
    -0.48
     composizione
    -0.48
    kable
    -0.47
    POSITIVE LOGITS
     виправивши
    0.73
     дописавши
    0.69
    Hochspringen
    0.63
     ivelany
    0.60
    ViewFeatures
    0.59
     disponibilités
    0.58
     Dinosaurs
    0.57
     sekret
    0.56
    quay
    0.56
    ToScroll
    0.56
    Activations Density 0.273%

    No Known Activations