© 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. 4206
    Prev
    Next
    INDEX
    Explanations

    patterns of computational layer activity characteristic of certain neural network processes

    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
    tableFuture
    -0.73
     referenties
    -0.72
     Buffett
    -0.71
     nahilalakip
    -0.71
    DockStyle
    -0.69
     Carthage
    -0.69
     Willoughby
    -0.69
    ATF
    -0.69
     GetEnumerator
    -0.67
     Buffet
    -0.67
    POSITIVE LOGITS
    FC
    3.20
     FC
    3.05
    fc
    2.52
     fc
    2.30
     Fc
    1.66
    Fc
    1.62
    FCS
    0.96
    xFC
    0.94
    fcn
    0.94
     Football
    0.86
    Activations Density 0.014%

    No Known Activations