© 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. 6-RES-MATRYOSHKA-DC
    7. 1545
    Prev
    Next
    INDEX
    Explanations

    bitwise operations involving left and right shifts, bitwise AND, and bitwise OR within what appears to be C code.

    oai_token-act-pair · gemini-2.0-flash
    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
    (
    -0.55
    addComponent
    -0.55
     equi
    -0.54
    вест
    -0.54
     null
    -0.52
    null
    -0.52
    {[
    -0.52
    <tbody>
    -0.52
    </b>
    -0.51
     ...
    -0.50
    POSITIVE LOGITS
     endforeach
    0.84
     Мексичка
    0.80
    WritableDatabase
    0.78
     timedelta
    0.76
     setw
    0.75
    Berikut
    0.74
    antaranya
    0.74
     IOError
    0.73
    FTFY
    0.71
     userRepository
    0.68
    Activations Density 0.250%

    No Known Activations