© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12909
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and parameters related to advanced statistical and mathematical modeling

    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
    FromArray
    -0.60
     connecting
    -0.57
     revanche
    -0.57
     participating
    -0.56
     ролях
    -0.55
     habet
    -0.54
    فایل‌لار
    -0.53
    Participating
    -0.53
     seuls
    -0.52
     Participating
    -0.52
    POSITIVE LOGITS
     estimating
    1.77
     Estimating
    1.55
     calculating
    1.28
    Estimating
    1.05
     Calculating
    0.89
     predicting
    0.87
     computing
    0.81
    calcul
    0.78
    estimating
    0.78
    Calculating
    0.73
    Activations Density 0.005%

    No Known Activations