© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    strings related to protein and gene names, especially those with numbers

    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
     AssemblyCulture
    -0.75
    
    -0.73
    msgSender
    -0.68
    +:+
    -0.68
    JsonHelper
    -0.67
     AssemblyVersion
    -0.67
    BeforeMethod
    -0.66
    MENAFN
    -0.64
     ivelany
    -0.64
     snippetHide
    -0.63
    POSITIVE LOGITS
     family
    0.70
     FAMILY
    0.56
     Family
    0.56
    Related
    0.55
     member
    0.54
     protein
    0.54
    family
    0.54
    soort
    0.54
    Family
    0.52
     Related
    0.50
    Activations Density 0.725%

    No Known Activations