© 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. 0-RES-MATRYOSHKA-DC
    7. 15767
    Prev
    Next
    INDEX
    Explanations

    instances of witnessing or observing an event

    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
     witnesses
    -1.73
    Witnesses
    -1.29
     Witnesses
    -1.27
     eyew
    -0.79
    NamedQueries
    -0.66
     testigos
    -0.59
    Faq
    -0.55
     témoins
    -0.53
     tenses
    -0.52
    LLVM
    -0.50
    POSITIVE LOGITS
     Witness
    1.26
     witness
    1.07
     witnessed
    1.07
    witness
    1.03
    Witness
    0.98
     witnessing
    0.93
     Chwiliwch
    0.69
    enterOuterAlt
    0.69
     mxArray
    0.68
    SequentialGroup
    0.68
    Activations Density 0.003%

    No Known Activations