© 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. 0-CLT-HP
    7. 95548
    Prev
    Next
    INDEX
    Explanations

    )

    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
    2
    -0.54
    1
    -0.51
    3
    -0.46
    4
    -0.45
    7
    -0.44
    k
    -0.41
    li
    -0.41
    8
    -0.41
    5
    -0.40
    par
    -0.39
    POSITIVE LOGITS
    MigrationBuilder
    1.31
    elemField
    1.04
     وتسجيلات
    1.02
     kaarangay
    1.01
    rrggbb
    1.01
    featureID
    1.00
     propOrder
    1.00
    BeginContext
    0.99
    MessageTagHelper
    0.98
     EconPapers
    0.98
    Activations Density 0.086%

    No Known Activations