© 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. 6614
    Prev
    Next
    INDEX
    Explanations

    structured data elements such as objects, arrays, or code blocks

    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
    DockStyle
    -0.86
    awtextra
    -0.73
    extAlignment
    -0.70
     autorytatywna
    -0.70
    expandindo
    -0.67
    sizeCache
    -0.64
     betweenstory
    -0.64
    WriteBarrier
    -0.63
    CppMethod
    -0.63
    曖昧さ回避
    -0.63
    POSITIVE LOGITS
    transQ
    0.60
     aload
    0.58
     فريبيس
    0.56
    RenderAtEndOf
    0.50
     usaha
    0.48
     obowią
    0.45
     možnost
    0.45
    arrête
    0.45
     aéreas
    0.45
     équilibre
    0.45
    Activations Density 0.569%

    No Known Activations