© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    Delta

    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
     المعيارى
    -0.72
    TestingModule
    -0.69
    ReusableCell
    -0.62
     שוליים
    -0.56
    setVerticalGroup
    -0.53
    arraycopy
    -0.52
    Portail
    -0.50
    ba
    -0.50
     BCA
    -0.49
    ViewImports
    -0.48
    POSITIVE LOGITS
    Dichloropropane
    0.68
     IV
    0.66
    ICLES
    0.52
     keo
    0.51
    IV
    0.51
     II
    0.50
    orney
    0.49
    MigrationBuilder
    0.49
    breadcrumbs
    0.48
    dolu
    0.48
    Activations Density 0.002%

    No Known Activations