© 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. 6862
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "upon" indicating the neuron detects instances of the word "upon" in the text

    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
    ing
    -0.82
    <?,
    -0.75
    Ria
    -0.68
    ING
    -0.65
    ి
    -0.60
    gging
    -0.59
    ghijklmnop
    -0.59
    DllImport
    -0.59
    curo
    -0.59
     Gutiérrez
    -0.58
    POSITIVE LOGITS
     upon
    3.19
    upon
    3.08
     UPON
    3.00
     Upon
    2.80
    Upon
    2.67
     apon
    1.52
     vpon
    1.21
     thereupon
    1.01
     asupra
    1.00
     upo
    0.95
    Activations Density 0.027%

    No Known Activations