© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    instances of the word "well" used as an adverb

    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
     Too
    -1.20
    too
    -1.16
    Too
    -1.16
     too
    -1.12
    TOO
    -1.00
     TOO
    -0.99
     слишком
    -0.82
     enough
    -0.81
     zbyt
    -0.77
    toos
    -0.75
    POSITIVE LOGITS
     also
    0.87
     aswell
    0.77
     även
    0.75
    also
    0.72
     également
    0.71
     виправивши
    0.71
     Also
    0.70
     също
    0.68
    Also
    0.67
     также
    0.67
    Activations Density 0.017%

    No Known Activations