© 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. 24799
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to modulo operations

    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
    AsUp
    -0.93
     Roskov
    -0.87
    hyrchwyd
    -0.71
     itſelf
    -0.71
     himo
    -0.70
     umbi
    -0.69
    omaly
    -0.69
    AccessorTable
    -0.69
    ubehör
    -0.68
    الحياه
    -0.68
    POSITIVE LOGITS
    мерть
    0.52
    kus
    0.50
    <em>
    0.48
     đích
    0.47
     und
    0.46
     job
    0.46
    bmod
    0.46
     string
    0.44
     ${
    0.44
    yszer
    0.44
    Activations Density 0.001%

    No Known Activations