© 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. 7403
    Prev
    Next
    INDEX
    Explanations

    references to filename variables in code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    География
    -0.62
     Sanitary
    -0.57
     rubio
    -0.57
     Stande
    -0.56
    abd
    -0.56
    ات
    -0.55
     pareti
    -0.55
    labilir
    -0.54
    ebilir
    -0.54
    _
    -0.53
    POSITIVE LOGITS
     filename
    2.78
    filename
    2.77
    Filename
    2.11
    FILENAME
    1.63
     filenames
    1.63
     Filename
    1.59
    FileName
    1.47
    filepath
    1.42
    filenames
    1.39
    文件名
    1.38
    Activations Density 0.007%

    No Known Activations