© 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. 2-RES-MATRYOSHKA-DC
    7. 2519
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "cast" used in code, indicating it detects the usage or presence of casting operations

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ViewFeatures
    -0.89
     للمعارف
    -0.73
     }}"></
    -0.69
    devamını
    -0.67
    windowFixed
    -0.64
    imakasih
    -0.63
     *)__
    -0.61
    estões
    -0.61
    ContentAlignment
    -0.59
     papiers
    -0.59
    POSITIVE LOGITS
     cast
    4.09
    cast
    3.92
    Cast
    3.86
     Cast
    3.81
     casts
    3.45
     CAST
    3.31
    CAST
    3.28
     casting
    3.14
    casts
    3.03
    casting
    2.91
    Activations Density 0.052%

    No Known Activations