© 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. 0-CLT-HP
    7. 94728
    Prev
    Next
    INDEX
    Explanations

    keel

    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
    Vidite
    -0.79
    parsedMessage
    -0.74
     XCTest
    -0.68
     nonatomic
    -0.66
    WebServlet
    -0.65
    invokeLater
    -0.65
     ligiloj
    -0.64
    __*/
    -0.63
    ніципа
    -0.63
    
    -0.63
    POSITIVE LOGITS
     kasarigan
    0.49
    发表于
    0.46
    d
    0.46
    es
    0.46
    ez
    0.43
    ek
    0.43
    lig
    0.42
    뀔
    0.42
     दृ
    0.42
     Fag
    0.41
    Activations Density 1.582%

    No Known Activations