© 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. 0-CLT-HP
    7. 43850
    Prev
    Next
    INDEX
    Explanations

    Legal publications

    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
    AsUp
    -0.70
     Mone
    -0.66
    Sucesor
    -0.64
    ondissement
    -0.61
    expandindo
    -0.59
    randomUUID
    -0.57
    tilia
    -0.57
    quita
    -0.57
     opérateur
    -0.57
    PositiveButton
    -0.56
    POSITIVE LOGITS
     jLabel
    0.59
     ویکی‌پدیای
    0.59
     jScrollPane
    0.54
     cdti
    0.52
     Paglinawan
    0.52
    хьтан
    0.51
     onCreateView
    0.50
     EconPapers
    0.50
    __":
    0.49
     tarp
    0.48
    Activations Density 1.748%

    No Known Activations