© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2583
    Prev
    Next
    INDEX
    Explanations

    was

    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
     the
    -0.71
     a
    -0.68
     another
    -0.64
     an
    -0.63
     important
    -0.57
     one
    -0.56
    脚注の使い方
    -0.54
     belangrij
    -0.54
     mourut
    -0.53
     different
    -0.53
    POSITIVE LOGITS
     AssemblyCulture
    0.66
    AutoScaleMode
    0.59
     Roskov
    0.59
     censiti
    0.59
     still
    0.55
     linkovi
    0.55
    intios
    0.55
    sendRedirect
    0.55
    IUrlHelper
    0.54
    stateProvider
    0.54
    Activations Density 0.005%

    No Known Activations