© 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. 10757
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to various functions and parameters in equations

    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
    Portail
    -0.85
    WEBPACK
    -0.74
    ių
    -0.73
    randomUUID
    -0.69
    aarrggbb
    -0.68
    resizingMask
    -0.67
     '<?
    -0.67
    انيف
    -0.67
    sertation
    -0.66
     resourceCulture
    -0.66
    POSITIVE LOGITS
     Ie
    0.62
    échelle
    0.61
    accompag
    0.59
    UrlResolution
    0.57
    entraî
    0.56
    obtenir
    0.56
    országban
    0.56
    Pt
    0.54
     poti
    0.54
    appré
    0.54
    Activations Density 0.161%

    No Known Activations