© 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. 3200
    Prev
    Next
    INDEX
    Explanations

    Personal anecdotes

    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
    RegressionTest
    -0.72
     CreateTagHelper
    -0.65
    modb
    -0.59
    msgTypes
    -0.58
    posedge
    -0.58
     оригіналу
    -0.56
     تضيفلها
    -0.55
     EconPapers
    -0.53
     kasarigan
    -0.51
     Reproduce
    -0.51
    POSITIVE LOGITS
     realize
    0.47
     BoxFit
    0.47
     发表于
    0.45
    ionView
    0.44
     referenties
    0.43
     bắt
    0.43
    PASO
    0.42
    webElementXpaths
    0.42
     realise
    0.41
     AssemblyProduct
    0.41
    Activations Density 0.001%

    No Known Activations