© 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. 94579
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
     EconPapers
    -0.77
    ContentAsync
    -0.65
    ReusableCell
    -0.61
    énario
    -0.59
     AssemblyCulture
    -0.57
    прочем
    -0.57
     Profitez
    -0.56
     مشين
    -0.56
     ujednoznacz
    -0.56
     Urbano
    -0.55
    POSITIVE LOGITS
     censiti
    0.68
    RegistryLite
    0.58
     متعلقه
    0.57
    InitVars
    0.53
    RegressionTest
    0.51
     '\\;'
    0.51
    ettet
    0.50
     OMITBAD
    0.49
    Traffic
    0.49
    RTLD
    0.48
    Activations Density 0.022%

    No Known Activations