© 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. 94093
    Prev
    Next
    INDEX
    Explanations

    5

    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
    protoimpl
    -0.72
    cshtml
    -0.62
     تضيفلها
    -0.57
     vivo
    -0.56
     mpl
    -0.56
    Subview
    -0.55
     pieces
    -0.55
    enumi
    -0.54
     sponsors
    -0.53
    хьтан
    -0.53
    POSITIVE LOGITS
    вості
    0.57
     duração
    0.53
     sanitaires
    0.53
    AssignableFrom
    0.51
    égique
    0.50
     AssemblyCulture
    0.50
     acrylique
    0.49
    (!)
    0.49
     postales
    0.49
     soucis
    0.49
    Activations Density 0.001%

    No Known Activations