© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1732
    Prev
    Next
    INDEX
    Explanations

    speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     speaking
    -1.45
    speaking
    -1.42
     Speaking
    -1.30
    Speaking
    -1.18
     parlant
    -1.02
     talking
    -0.97
    talking
    -0.96
     hablando
    -0.94
     Talking
    -0.81
    Talking
    -0.73
    POSITIVE LOGITS
     to
    0.75
    фак
    0.61
     with
    0.60
     about
    0.60
     of
    0.52
    
    0.49
    PMailer
    0.49
    ogram
    0.47
     generally
    0.46
    KommentareTeilen
    0.45
    Activations Density 0.063%

    No Known Activations