© 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. 20-CLT-HP
    7. 73212
    Prev
    Next
    INDEX
    Explanations

    general writing/tech contexts

    np_max-act-logits · 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
     vectorielles
    -0.66
     lourdes
    -0.59
    webElementXpaths
    -0.57
     industriels
    -0.57
    الحياه
    -0.57
    hiva
    -0.57
    jangkau
    -0.56
     définiti
    -0.56
     privées
    -0.52
     majeurs
    -0.52
    POSITIVE LOGITS
    __(/*!
    0.57
     di
    0.57
     with
    0.55
    GEBURTSDATUM
    0.50
    )}_
    0.50
     GRATU
    0.47
    unteer
    0.47
    with
    0.47
    WriteTagHelper
    0.47
     Asegúrese
    0.46
    Activations Density 0.000%

    No Known Activations