© 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. 3976
    Prev
    Next
    INDEX
    Explanations

    the computational process involved in training and using artificial neural networks

    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
    CloseOperation
    -0.88
    contentLoaded
    -0.77
    InjectAttribute
    -0.74
    AppMethodBeat
    -0.73
     Sardin
    -0.68
     للاسماء
    -0.68
     Roskov
    -0.68
    WriteAttribute
    -0.66
    AndEndTag
    -0.66
     itemprop
    -0.65
    POSITIVE LOGITS
    nn
    0.60
    NN
    0.56
    ultas
    0.56
    openConnection
    0.54
    ReLU
    0.53
    __()
    0.48
     nn
    0.45
    LSTM
    0.44
    cnn
    0.42
    denn
    0.42
    Activations Density 0.215%

    No Known Activations