© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15332
    Prev
    Next
    INDEX
    Explanations

    references to speaking or verbal communication

    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
     speaks
    -0.60
     speak
    -0.57
    <<"\
    -0.56
    Hozzáférés
    -0.54
     spoke
    -0.54
     Spo
    -0.54
     hablan
    -0.52
     talking
    -0.52
     Speak
    -0.50
    spoke
    -0.50
    POSITIVE LOGITS
     Speaking
    1.91
    speaking
    1.90
     speaking
    1.87
    Speaking
    1.80
     parlant
    0.93
     rzecz
    0.89
     Efq
    0.79
    ]--;
    0.68
     говоря
    0.66
     gezien
    0.65
    Activations Density 0.012%

    No Known Activations