© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    references to software versioning and configuration details

    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
     NSCoder
    -0.74
     doInBackground
    -0.72
    EndInit
    -0.69
    UnsafeEnabled
    -0.68
    ReusableCell
    -0.63
     Sarm
    -0.62
    ClientSize
    -0.60
     بيها
    -0.60
     فريبيس
    -0.60
     виправивши
    -0.58
    POSITIVE LOGITS
    fileID
    6.00
    fileId
    1.09
    tangentMode
    1.00
     file
    0.90
    file
    0.90
    File
    0.89
     File
    0.87
    FILE
    0.80
    classID
    0.79
     FILE
    0.74
    Activations Density 0.001%

    No Known Activations