© 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. 1-CLT-HP
    7. 13412
    Prev
    Next
    INDEX
    Explanations

    play

    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
    game
    -0.70
     joué
    -0.69
     juego
    -0.69
     played
    -0.68
    play
    -0.67
     play
    -0.66
     giocare
    -0.65
     žaid
    -0.65
    playing
    -0.65
     jouer
    -0.62
    POSITIVE LOGITS
     صوتيه
    0.75
    OGND
    0.59
    styleType
    0.57
    setupUi
    0.57
     LoggerFactory
    0.55
    able
    0.54
     algorithms
    0.52
    SourceChecksum
    0.51
    UnknownFields
    0.51
    ctose
    0.50
    Activations Density 0.051%

    No Known Activations