© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    Microsoft code snippets including Windows and Azure

    oai_token-act-pair · gemini-2.0-flash
    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
    ConstraintMaker
    -0.80
    SequentialGroup
    -0.76
     ویکی‌پدیا
    -0.75
     Chwiliwch
    -0.71
     estekak
    -0.69
    ########.
    -0.69
     ivelany
    -0.69
    InputBorder
    -0.68
    zerland
    -0.66
    脚注の使い方
    -0.66
    POSITIVE LOGITS
     Microsoft
    1.26
    Microsoft
    1.21
     microsoft
    1.14
    microsoft
    1.13
    Xaml
    0.96
    HRESULT
    0.93
     Windows
    0.92
     Xbox
    0.89
    Windows
    0.87
    微软
    0.82
    Activations Density 1.083%

    No Known Activations