© 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. 24-RES-MATRYOSHKA-DC
    7. 1475
    Prev
    Next
    INDEX
    Explanations

    medical research papers and articles

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    '])){
    -0.59
    rungsseite
    -0.56
    RSpec
    -0.51
    !("
    -0.49
    verwijspagina
    -0.48
    >`
    -0.47
    념
    -0.46
     isKindOfClass
    -0.44
    adə
    -0.44
    ']))
    -0.43
    POSITIVE LOGITS
     Abstract
    0.91
    Abstract
    0.82
    BACKGROUND
    0.82
     BACKGROUND
    0.82
     ABSTRACT
    0.77
     abstract
    0.76
    <eos>
    0.76
     Journal
    0.75
     OBJECTIVE
    0.71
    Background
    0.71
    Activations Density 1.718%

    No Known Activations