© 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-CLT-HP
    7. 38405
    Prev
    Next
    INDEX
    Explanations

    talking

    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
     talking
    -1.64
    talking
    -1.32
     Talking
    -1.07
     talkin
    -1.02
    Talking
    -0.96
     thinking
    -0.83
    thinking
    -0.73
     messaging
    -0.63
     Thinking
    -0.58
    ɚ
    -0.57
    POSITIVE LOGITS
     estimés
    0.77
    Demikian
    0.67
     refusé
    0.64
     disparu
    0.64
    ValueStyle
    0.63
     htons
    0.61
    ública
    0.60
     typelib
    0.59
    moveToFirst
    0.59
     Audiodateien
    0.58
    Activations Density 0.770%

    No Known Activations