© 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. 97225
    Prev
    Next
    INDEX
    Explanations

    but

    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
     but
    -0.76
     joten
    -0.59
     tetapi
    -0.54
    but
    -0.52
     asemenea
    -0.52
    gående
    -0.50
     allmän
    -0.50
     hanem
    -0.47
     takže
    -0.47
     varmt
    -0.46
    POSITIVE LOGITS
     متعلقه
    1.05
     ivelany
    1.01
     nahilalakip
    0.99
     CreateTagHelper
    0.87
     مرئيه
    0.84
     unknownFields
    0.78
     ***!
    0.77
    agaimana
    0.75
     surla
    0.75
    protoimpl
    0.75
    Activations Density 0.078%

    No Known Activations