© 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. 0-CLT-HP
    7. 1585
    Prev
    Next
    INDEX
    Explanations

    contact

    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
     contact
    -1.05
    contact
    -0.86
     Contact
    -0.82
    Contact
    -0.78
     CONTACT
    -0.72
     contacts
    -0.69
     contacted
    -0.65
     kontakt
    -0.65
     contacto
    -0.64
    CONTACT
    -0.63
    POSITIVE LOGITS
    RegressionTest
    0.64
    Tikang
    0.64
    ISupport
    0.62
     sessionFactory
    0.61
     MainAxisSize
    0.61
     craters
    0.60
    MemoryWarning
    0.60
    onomía
    0.60
     flamma
    0.59
    êng
    0.59
    Activations Density 1.077%

    No Known Activations