© 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. 1-RES-MATRYOSHKA-DC
    7. 201
    Prev
    Next
    INDEX
    Explanations

    code snippets or comments related to file operations and 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
     number
    -0.75
    fjspx
    -0.66
    number
    -0.64
     numbers
    -0.63
     Number
    -0.62
    lineEdit
    -0.61
     número
    -0.58
    numbers
    -0.57
     ClassNotFound
    -0.56
     ExecuteAsync
    -0.56
    POSITIVE LOGITS
    //
    3.23
    //
    2.59
     //
    2.45
    ///
    2.20
    /*
    2.11
    )//
    2.05
    ////
    2.02
    +//
    1.89
    ,//
    1.86
    -//
    1.80
    Activations Density 0.675%

    No Known Activations