© 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. 11777
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and operations, specifically parsing and handling numerical values

    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
    حياته
    -0.51
    '/',
    -0.49
     lengths
    -0.48
     IntPtr
    -0.48
     kilom
    -0.48
    Xna
    -0.47
    byte
    -0.47
    высо
    -0.47
     human
    -0.45
     WRIT
    -0.45
    POSITIVE LOGITS
    parseDouble
    1.01
    strconv
    0.97
    TryParse
    0.88
    NameInMap
    0.82
    endphp
    0.79
    parseColor
    0.76
    Atoi
    0.75
    mybatisplus
    0.73
     ویکی‌پدیای
    0.71
    parseInt
    0.70
    Activations Density 0.008%

    No Known Activations