© 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. 24347
    Prev
    Next
    INDEX
    Explanations

    references to specific genetic markers associated with diseases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.65
     Tep
    -0.60
    Tikang
    -0.57
     Tea
    -0.57
    ees
    -0.56
     Piro
    -0.56
    nito
    -0.55
     bero
    -0.54
     brig
    -0.54
    **************
    -0.53
    POSITIVE LOGITS
     CR
    0.89
    aguya
    0.85
    CR
    0.82
    Хьажоргаш
    0.82
     inflater
    0.79
     crucero
    0.77
    modb
    0.76
    featureID
    0.75
     pétrole
    0.75
     CRISPR
    0.72
    Activations Density 0.023%

    No Known Activations