© 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. 1-CLT-HP
    7. 46251
    Prev
    Next
    INDEX
    Explanations

    aged

    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
    migrationBuilder
    -0.60
    Portale
    -0.51
     web
    -0.47
    <bos>
    -0.45
    queryInterface
    -0.44
    tonsoft
    -0.44
    ToScroll
    -0.43
    TypedDataSet
    -0.42
     uska
    -0.42
     in
    -0.41
    POSITIVE LOGITS
     Chriftian
    0.69
    +#+#
    0.65
     Monfieur
    0.64
     fubject
    0.62
     Diſ
    0.62
    saraba
    0.60
    WriteTagHelper
    0.60
     ciga
    0.60
     chi̍t
    0.60
     Tampoco
    0.60
    Activations Density 0.009%

    No Known Activations