© 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. 4-CLT-HP
    7. 803
    Prev
    Next
    INDEX
    Explanations

    manufacturers

    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
    はじめに
    -0.57
    esgue
    -0.50
     المعيارى
    -0.45
    íslu
    -0.45
    Slf
    -0.41
    elasticsearch
    -0.41
     XCTest
    -0.41
     Computers
    -0.41
     Circuits
    -0.40
    THISDAY
    -0.40
    POSITIVE LOGITS
    :✨
    0.76
    zeß
    0.65
    fromnode
    0.63
     asking
    0.59
     indisponible
    0.58
    useppe
    0.58
    Rate
    0.57
     rate
    0.57
    NECTION
    0.56
     Pires
    0.56
    Activations Density 0.004%

    No Known Activations