© 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. 20957
    Prev
    Next
    INDEX
    Explanations

    mathematical values and symbols, particularly in the context of research papers or mathematical terminology

    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
    ه‌اند
    -0.61
     grà
    -0.59
     chó
    -0.57
     '*':
    -0.57
     '-';
    -0.56
     nakalista
    -0.56
     '-':
    -0.56
     fieldNum
    -0.56
     Aner
    -0.53
     Derfor
    -0.53
    POSITIVE LOGITS
     ویکی‌پدیا
    0.57
    ServiceProvider
    0.57
    AddHtmlAttribute
    0.56
    antaine
    0.49
     ویکی‌پدیای
    0.48
    ArgsConstructor
    0.47
     محفوظة
    0.45
    NewUrlParser
    0.45
     gouttes
    0.44
    رشف
    0.43
    Activations Density 0.013%

    No Known Activations