© 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. 2-RES-MATRYOSHKA-DC
    7. 4559
    Prev
    Next
    INDEX
    Explanations

    focuses on identifying mathematical expressions involving weighted averages or derivatives, particularly those related to complex statistical or physical formulas

    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
    autonomie
    -0.63
    जू
    -0.62
    Varint
    -0.60
     observing
    -0.57
    еве
    -0.57
    IRD
    -0.54
     capacities
    -0.54
     Independent
    -0.53
    capacity
    -0.53
     capacity
    -0.52
    POSITIVE LOGITS
     weighted
    2.84
     Weighted
    2.61
    weighted
    2.59
    Weighted
    2.42
     weighting
    1.37
     weighed
    0.98
    weighed
    0.94
    rungsseite
    0.89
     cherchés
    0.66
     kasarigan
    0.63
    Activations Density 0.011%

    No Known Activations