© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical markup patterns

    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
    ↵↵
    -0.66
    <eos>
    -0.53
     My
    -0.52
      
    -0.49
     \\
    -0.48
     par
    -0.46
    にか
    -0.45
     in
    -0.44
     службы
    -0.44
     II
    -0.44
    POSITIVE LOGITS
     cherchés
    1.11
    GraphicsUnit
    0.94
    
    0.91
     propOrder
    0.90
    awtextra
    0.89
    astify
    0.89
     Italijanski
    0.89
    PMailer
    0.88
     resourceCulture
    0.88
    CppMethod
    0.86
    Activations Density 0.201%

    No Known Activations