© 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. 5-CLT-HP
    7. 737
    Prev
    Next
    INDEX
    Explanations

    weather

    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
     فريبيس
    -0.50
     Shields
    -0.41
     съм
    -0.39
    థ
    -0.38
     R
    -0.38
    Skate
    -0.38
    μαι
    -0.37
    InvalidProtocol
    -0.37
    Disable
    -0.36
    indon
    -0.36
    POSITIVE LOGITS
     useAppContext
    0.69
     يتيمه
    0.68
    awtextra
    0.67
    Serviço
    0.65
     Infórmanos
    0.65
     contextLoads
    0.65
    URLException
    0.64
     itſelf
    0.64
    RenderAtEndOf
    0.63
    yntaxException
    0.62
    Activations Density 0.002%

    No Known Activations