© 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. 92405
    Prev
    Next
    INDEX
    Explanations

    meaningful

    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
    DrawerToggle
    -0.70
     otomatig
    -0.70
     Италијани
    -0.69
    AndroidJUnit
    -0.67
     JAXBElement
    -0.66
     Italijani
    -0.66
     Vikipedi
    -0.59
    queryInterface
    -0.59
    MigrationBuilder
    -0.59
    RegressionTest
    -0.57
    POSITIVE LOGITS
    enumi
    0.54
    гля
    0.51
    omia
    0.44
    ----</
    0.43
     AssemblyCompany
    0.43
     المعيارى
    0.42
    гляд
    0.42
    delig
    0.42
    \{\\
    0.41
    grounded
    0.41
    Activations Density 0.000%

    No Known Activations