© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9912
    Prev
    Next
    INDEX
    Explanations

    Amin/Amar

    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
     AM
    -0.55
     <=",
    -0.51
     amide
    -0.51
    lent
    -0.50
     AMR
    -0.50
    AM
    -0.50
     am
    -0.49
     amine
    -0.47
     chio
    -0.47
    Am
    -0.47
    POSITIVE LOGITS
    +#+#
    0.75
    Décès
    0.72
    RenderAtEndOf
    0.63
     CreateTagHelper
    0.63
    WebElementEntity
    0.62
    ViewFeatures
    0.61
     '\\;'
    0.59
    LayoutInflater
    0.57
    TestTools
    0.57
     ujednoznacz
    0.56
    Activations Density 0.023%

    No Known Activations