© 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. 8-RES-MATRYOSHKA-DC
    7. 29628
    Prev
    Next
    INDEX
    Explanations

    the word "witness."

    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
     Putra
    -0.80
    İY
    -0.73
    QtWidgets
    -0.65
    RAINE
    -0.63
     Rak
    -0.62
    CGRectMake
    -0.61
     himſelf
    -0.61
    adne
    -0.60
    ьере
    -0.60
    ξύ
    -0.60
    POSITIVE LOGITS
     witness
    1.30
     Witness
    1.30
     witnesses
    1.29
    Witness
    1.24
    witness
    1.23
     Witnesses
    1.17
     WITNESS
    1.09
    Witnesses
    1.08
    nessed
    0.99
     témoins
    0.96
    Activations Density 0.011%

    No Known Activations