© 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. 40421
    Prev
    Next
    INDEX
    Explanations

    general text

    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
     in
    -0.45
    viewType
    -0.43
    وردار
    -0.42
    chließend
    -0.41
    当
    -0.40
     prior
    -0.40
     ov
    -0.40
    當
    -0.39
     globe
    -0.39
    .
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.89
     CreateTagHelper
    0.81
     الرياضيه
    0.80
    findpost
    0.79
    resave
    0.79
     فريبيس
    0.77
     JAXBElement
    0.77
    Bronnen
    0.76
    UnusedPrivate
    0.76
     okuyayım
    0.74
    Activations Density 0.012%

    No Known Activations