© 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. 92366
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
    MENAFN
    -0.75
    endphp
    -0.68
    ConverterFactory
    -0.65
    sin
    -0.63
    sit
    -0.61
    a
    -0.61
    으로
    -0.60
     Reverso
    -0.60
    ylase
    -0.59
    ness
    -0.59
    POSITIVE LOGITS
    MemoryWarning
    0.62
     plais
    0.52
    getDoctrine
    0.52
     consultato
    0.50
     épa
    0.50
     desplazamiento
    0.50
     venons
    0.49
    hind
    0.49
    DMETHOD
    0.48
     récomp
    0.48
    Activations Density 1.549%

    No Known Activations