© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3211
    Prev
    Next
    INDEX
    Explanations

    lines of code related to data manipulation and processing, especially involving dataframe operations and array handling

    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
    SourceChecksum
    -1.12
    ()")
    -0.81
     calendriers
    -0.81
    */),
    -0.80
    .")
    -0.79
     nahilalakip
    -0.77
     Normdatei
    -0.77
    ".
    -0.74
     препратки
    -0.74
    ()",
    -0.73
    POSITIVE LOGITS
    df
    2.94
     df
    2.55
    DF
    2.36
     DF
    1.95
    Df
    1.52
    dfs
    1.13
     Df
    1.10
     dataframe
    1.06
    xdf
    0.94
    dfd
    0.93
    Activations Density 0.011%

    No Known Activations