© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6079
    Prev
    Next
    INDEX
    Explanations

    not, to

    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
    Negative Logits
    KommentareTeilen
    -0.76
     Мексичка
    -0.69
     cardiaque
    -0.64
     fédé
    -0.64
     animés
    -0.61
    adaptiveStyles
    -0.61
     measured
    -0.60
     تضيفلها
    -0.60
     fermés
    -0.59
     meurt
    -0.59
    POSITIVE LOGITS
     OFDb
    0.51
    setViewportView
    0.49
    SpringRunner
    0.48
    String
    0.48
     iNdEx
    0.47
    AndPassword
    0.47
     String
    0.44
    +#+#
    0.42
    RegressionTest
    0.42
     дописавши
    0.41
    Activations Density 0.002%

    No Known Activations