© 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. 9561
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical digits in various contexts

    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
    u
    -0.54
    Rourke
    -0.53
    kuuta
    -0.52
     referrerpolicy
    -0.50
     Ragnarok
    -0.50
     aras
    -0.49
    a
    -0.49
    ūras
    -0.47
    太郎
    -0.47
    k
    -0.47
    POSITIVE LOGITS
     digits
    1.55
     digit
    1.38
    digits
    1.37
     Digit
    1.31
    digit
    1.19
     DIGIT
    1.19
    Digits
    1.18
    Digit
    1.16
    DIGIT
    1.11
     Efq
    1.05
    Activations Density 0.002%

    No Known Activations