© 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. 18664
    Prev
    Next
    INDEX
    Explanations

    references to casting in programming or technical contexts

    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
    ViewFeatures
    -1.13
     photolibrary
    -1.08
    ergies
    -1.05
    SBATCH
    -1.01
     Мексичка
    -1.00
     Gurney
    -0.99
    crapers
    -0.94
     xenia
    -0.94
    ^(@)
    -0.94
     }}"></
    -0.93
    POSITIVE LOGITS
     Cast
    1.77
     CAST
    1.59
    Cast
    1.52
     cast
    1.50
     Kast
    1.42
    cast
    1.39
    Kast
    1.38
     casts
    1.27
    CAST
    1.26
     Castor
    1.23
    Activations Density 0.035%

    No Known Activations