© 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. 90863
    Prev
    Next
    INDEX
    Explanations

    internet and web

    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
    were
    -0.56
     for
    -0.48
     to
    -0.46
    Are
    -0.45
    Were
    -0.44
    are
    -0.44
     Were
    -0.43
     WERE
    -0.42
     were
    -0.42
     Are
    -0.39
    POSITIVE LOGITS
    AndroidJUnit
    0.85
    GraphicsUnit
    0.79
    featureID
    0.77
    IUrlHelper
    0.74
     snippetHide
    0.73
    MigrationBuilder
    0.70
     allows
    0.70
    ंदीखरीदारी
    0.69
    AddTagHelper
    0.68
     has
    0.68
    Activations Density 0.001%

    No Known Activations