© 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. 32583
    Prev
    Next
    INDEX
    Explanations

    format-related elements commonly used in email texts

    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
     chi̍t
    -0.69
     nahilalakip
    -0.68
    essages
    -0.60
     acceptez
    -0.59
    وفاته
    -0.58
     cremallera
    -0.56
    rrggbb
    -0.56
     ddelweddau
    -0.55
    GEBURTSDATUM
    -0.55
    unknownFields
    -0.55
    POSITIVE LOGITS
    
    0.75
     AssemblyCompany
    0.63
    ftagPool
    0.54
     محفوظة
    0.52
     SafeMath
    0.50
     shifts
    0.49
    then
    0.48
    modelBuilder
    0.46
    PostExecute
    0.46
     UFC
    0.45
    Activations Density 0.002%

    No Known Activations