© 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. 2517
    Prev
    Next
    INDEX
    Explanations

    English language and programming

    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
    からです
    -0.71
     namelijk
    -0.67
     totiž
    -0.67
     nemlig
    -0.66
    Viitteet
    -0.60
     nämlich
    -0.57
     justement
    -0.51
     bowiem
    -0.50
    staticmethod
    -0.49
     justamente
    -0.49
    POSITIVE LOGITS
    SharedDtor
    0.71
    Бахар
    0.58
     entanto
    0.57
     typelib
    0.56
    voorbeeld
    0.56
    StructEnd
    0.55
    postmedia
    0.54
     CreateTagHelper
    0.54
    #+#
    0.52
    CloseOperation
    0.51
    Activations Density 0.003%

    No Known Activations