© 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. 1633
    Prev
    Next
    INDEX
    Explanations

    swoop

    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
     nakalista
    -0.84
    actus
    -0.83
    orated
    -0.70
     intermédiaire
    -0.65
    RetentionPolicy
    -0.64
    MigrationBuilder
    -0.64
     Efq
    -0.61
     useStyles
    -0.60
    adás
    -0.59
     relâche
    -0.59
    POSITIVE LOGITS
    痹
    0.59
    はじめに
    0.56
    ****
    0.48
    ances
    0.46
     Bluestacks
    0.45
    cox
    0.45
    enegro
    0.44
    醐
    0.44
    autoconfigure
    0.43
    ****************
    0.43
    Activations Density 1.650%

    No Known Activations