© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1450
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
     ma
    -0.38
     surla
    -0.37
     land
    -0.37
     reiv
    -0.35
    гле
    -0.35
    Ầ
    -0.35
    kom
    -0.34
     look
    -0.34
     taste
    -0.34
    richter
    -0.34
    POSITIVE LOGITS
    WithIOException
    0.87
    Tetapi
    0.81
    Personendaten
    0.79
     ostavi
    0.71
    expandindo
    0.70
    )";
    0.68
    )");
    0.66
    IVEREF
    0.66
     propOrder
    0.66
    CodeAnalysis
    0.66
    Activations Density 0.001%

    No Known Activations