© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4040
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    ania
    -0.41
    cy
    -0.40
    tain
    -0.39
    ial
    -0.39
    veel
    -0.38
    ty
    -0.36
    ology
    -0.36
    ul
    -0.35
    try
    -0.35
    ality
    -0.35
    POSITIVE LOGITS
    CloseOperation
    0.84
     surla
    0.81
    RegistryLite
    0.78
     TabLayout
    0.76
     ChromeDriver
    0.75
    TestingModule
    0.75
     ✭✭
    0.75
    
    0.75
    djangoproject
    0.74
    ⓘ
    0.74
    Activations Density 0.000%

    No Known Activations