© 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. 40398
    Prev
    Next
    INDEX
    Explanations

    xa

    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
    xa
    -0.71
     rom
    -0.60
    JsonHelper
    -0.54
    tuvo
    -0.52
    xA
    -0.50
    rc
    -0.50
    flow
    -0.48
    IntoConstraints
    -0.48
    CPtr
    -0.46
    leitung
    -0.45
    POSITIVE LOGITS
     lenker
    0.80
    Pyx
    0.72
    كويكب
    0.69
    }\]
    0.61
    MemoryWarning
    0.60
    anță
    0.60
    enheim
    0.57
    erapeu
    0.57
    atuan
    0.56
    wachsene
    0.55
    Activations Density 1.643%

    No Known Activations