© 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. 4-CLT-HP
    7. 4658
    Prev
    Next
    INDEX
    Explanations

    children

    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
     متعلقه
    -0.57
    jooq
    -0.56
    Tikang
    -0.54
    ParallelGroup
    -0.53
    /*
    -0.52
     nahilalakip
    -0.51
    loroethene
    -0.50
    خصة
    -0.49
    AccessorTable
    -0.48
    ViewFeatures
    -0.47
    POSITIVE LOGITS
    Portail
    0.57
    ộn
    0.54
     चीज़ों
    0.54
     shepherds
    0.52
    Geplaatst
    0.51
     Rossa
    0.49
     Levant
    0.48
    setContentView
    0.48
     privatisation
    0.48
    OfDay
    0.48
    Activations Density 0.009%

    No Known Activations