© 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. 94422
    Prev
    Next
    INDEX
    Explanations

    many

    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
    -0.59
     podjela
    -0.54
     ModelAndView
    -0.53
     AssemblyVersion
    -0.50
    PerformLayout
    -0.49
    posedge
    -0.49
    oa̍t
    -0.48
    Искәрмәләр
    -0.46
    сылкі
    -0.46
    ódz
    -0.45
    POSITIVE LOGITS
     gräns
    0.60
    цездатний
    0.57
    zony
    0.56
    Архівовано
    0.55
    SpringBootTest
    0.54
     unknownFields
    0.54
    stagland
    0.53
     that
    0.52
    vician
    0.52
    ApplicationTests
    0.52
    Activations Density 0.003%

    No Known Activations