© 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. 1-CLT-HP
    7. 10082
    Prev
    Next
    INDEX
    Explanations

    electronic systems/devices

    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
     électronique
    -0.78
     elektron
    -0.77
    electronic
    -0.77
     elettron
    -0.73
     electronic
    -0.73
    Electronic
    -0.71
     Electronic
    -0.69
     elektronik
    -0.69
     électroniques
    -0.68
     electrónica
    -0.67
    POSITIVE LOGITS
    principalColumn
    0.53
    ůměr
    0.50
    Ranks
    0.47
    `,
    0.46
    MemoryWarning
    0.46
    $,
    0.45
    )";
    0.44
    Попис
    0.44
     लेकर
    0.43
     utilis
    0.42
    Activations Density 0.052%

    No Known Activations