© 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. 20-CLT-HP
    7. 71519
    Prev
    Next
    INDEX
    Explanations

    programming/technical specific language

    np_max-act-logits · 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
    Попис
    -0.53
     jib
    -0.51
    DoubleQuotes
    -0.51
    bux
    -0.50
    ✨:
    -0.50
     Eche
    -0.49
    SqlClient
    -0.49
    ])+
    -0.49
    ();)
    -0.49
    liothèque
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    expandindo
    0.64
    Clik
    0.55
    RegressionTest
    0.53
    HttpFoundation
    0.51
    <tfoot>
    0.50
    fes
    0.49
    ñores
    0.49
    UnitTesting
    0.49
     confé
    0.48
    Activations Density 0.003%

    No Known Activations