© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    references to waking up

    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
    localctx
    -0.62
     numberOfRows
    -0.60
    CrossRef
    -0.58
     виправивши
    -0.55
     francès
    -0.53
     pinulongan
    -0.52
    awtextra
    -0.50
    @[+][
    -0.50
    ніципалі
    -0.50
    SharedCtor
    -0.50
    POSITIVE LOGITS
     wake
    3.39
     wakes
    3.05
     Wake
    2.97
    wake
    2.97
    Wake
    2.91
     woke
    2.86
     waking
    2.86
     woken
    2.78
     awake
    2.41
     awoke
    2.41
    Activations Density 0.037%

    No Known Activations