© 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. 1-CLT-HP
    7. 45948
    Prev
    Next
    INDEX
    Explanations

    math

    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
     الرياضيه
    -0.56
     dead
    -0.55
    SharedCtor
    -0.54
     насељу
    -0.54
    énario
    -0.53
     empire
    -0.52
    contentLoaded
    -0.52
    jaros
    -0.51
     imperial
    -0.51
     Empire
    -0.50
    POSITIVE LOGITS
     motivadoras
    0.62
     leçons
    0.60
     varandra
    0.60
     mauvaises
    0.58
     preuves
    0.58
     complejidad
    0.57
     dommages
    0.57
     stället
    0.57
     especiais
    0.56
     conseguenze
    0.56
    Activations Density 0.222%

    No Known Activations