© 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. 3-RES-MATRYOSHKA-DC
    7. 2041
    Prev
    Next
    INDEX
    Explanations

    the verb "do"

    oai_token-act-pair · gemini-2.0-flash
    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
     ſtate
    -0.75
    DOES
    -0.75
    Does
    -0.70
     enfans
    -0.70
     Monfieur
    -0.68
     fubject
    -0.68
     ftate
    -0.66
     auffi
    -0.66
     Does
    -0.65
    theless
    -0.65
    POSITIVE LOGITS
     doing
    1.50
    Doing
    1.43
     done
    1.38
     Doing
    1.34
    doing
    1.25
     DOING
    1.18
     Done
    1.09
    Done
    1.03
     DONE
    1.00
     doin
    1.00
    Activations Density 0.140%

    No Known Activations