© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92693
    Prev
    Next
    INDEX
    Explanations

    having

    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
     associating
    -0.57
     defining
    -0.53
    setting
    -0.52
     sponsoring
    -0.50
     comparing
    -0.50
     showing
    -0.50
     generating
    -0.50
     spreading
    -0.49
     appearing
    -0.49
     demonstrating
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.63
     Савезне
    0.60
    nologue
    0.54
    IUrlHelper
    0.52
    nictví
    0.52
    requestCode
    0.50
     rent
    0.49
    wpi
    0.48
     StatefulWidget
    0.48
    RegressionTest
    0.48
    Activations Density 0.002%

    No Known Activations