© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12480
    Prev
    Next
    INDEX
    Explanations

    neurons that identify instances of the communication act

    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
    ">#
    -0.50
    はじめに
    -0.50
     Communications
    -0.48
    ﹃
    -0.47
    preprocessing
    -0.47
    ")==
    -0.47
    Communications
    -0.46
    newpage
    -0.46
     <",
    -0.46
    communications
    -0.45
    POSITIVE LOGITS
     communicate
    2.11
     communicates
    1.91
     communicated
    1.80
     communicating
    1.79
    communicate
    1.69
     Communicate
    1.66
     Communicating
    1.52
     COMMUNIC
    1.35
     communiquer
    1.09
     comunicar
    1.06
    Activations Density 0.002%

    No Known Activations