© 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. 11668
    Prev
    Next
    INDEX
    Explanations

    instances of the "printf" function in programming code

    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
    DRO
    -0.59
    ër
    -0.59
     Bell
    -0.57
    pole
    -0.57
     Drop
    -0.57
    drop
    -0.55
     Wak
    -0.55
    model
    -0.54
     drop
    -0.54
     côn
    -0.54
    POSITIVE LOGITS
    printf
    1.34
     printf
    1.23
    stdio
    1.21
    cstdio
    1.09
     AssemblyTitle
    1.05
    WebControls
    0.99
     scanf
    0.89
    %%%
    0.86
    httphttps
    0.85
    scanf
    0.84
    Activations Density 0.002%

    No Known Activations