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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3231
    Prev
    Next
    INDEX
    Explanations

    be

    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
    EndInit
    -0.68
     AssemblyCompany
    -0.59
     religieuses
    -0.54
     referenties
    -0.52
    InvalidProtocol
    -0.52
     đứng
    -0.49
    جغرافيا
    -0.48
     représent
    -0.48
     '\\;'
    -0.47
     maleta
    -0.47
    POSITIVE LOGITS
    ม้
    0.58
    IFORN
    0.54
     ironic
    0.52
     modelAndView
    0.52
     great
    0.52
     odd
    0.52
    RegressionTest
    0.52
     idea
    0.52
     ick
    0.51
     Drop
    0.51
    Activations Density 0.001%

    No Known Activations