© 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. 10300
    Prev
    Next
    INDEX
    Explanations

    arxyn

    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
    arynx
    -2.11
    aryngeal
    -1.02
     pharynx
    -0.82
    ImageIO
    -0.59
    Zeneca
    -0.59
     XCTest
    -0.59
     larynx
    -0.59
    ichthys
    -0.57
    ulity
    -0.57
    htbp
    -0.57
    POSITIVE LOGITS
     محفوظة
    0.59
     незавершена
    0.52
    Poloha
    0.50
    +#+#
    0.50
     الحره
    0.49
    μφωνα
    0.46
    awtextra
    0.45
    lines
    0.41
    存于互联网档案馆
    0.41
     Ather
    0.40
    Activations Density 0.015%

    No Known Activations