© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15773
    Prev
    Next
    INDEX
    Explanations

    activity related to a specific biochemical compound or molecule

    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
     tör
    -0.58
     Coyle
    -0.57
     métier
    -0.57
     verrez
    -0.56
     Py
    -0.55
    ellum
    -0.55
     boletos
    -0.55
     SafeMath
    -0.54
     kwargs
    -0.53
     supérieurs
    -0.53
    POSITIVE LOGITS
     cy
    2.25
    CloseOperation
    0.74
    fromnode
    0.69
     gynhyrchwyd
    0.68
    IntoConstraints
    0.67
    omock
    0.65
     للمعارف
    0.60
     Tramp
    0.60
    PRNewswire
    0.60
     cipher
    0.59
    Activations Density 0.001%

    No Known Activations