© 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. 43755
    Prev
    Next
    INDEX
    Explanations

    varied, music, opinions

    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
     Berk
    -1.27
    opers
    -0.93
    urably
    -0.70
     مرئيه
    -0.66
    ADELPHIA
    -0.65
    ylvan
    -0.65
    __*/
    -0.63
    MessageTagHelper
    -0.63
     HasFactory
    -0.61
    )_/¯
    -0.60
    POSITIVE LOGITS
     betweenstory
    0.60
     unité
    0.53
    RegressionTest
    0.52
     Eſ
    0.48
     Etrus
    0.47
     myſelf
    0.47
    ſelf
    0.47
     itſelf
    0.46
     unit
    0.46
     Tienen
    0.45
    Activations Density 0.109%

    No Known Activations