© 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. 77339
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
     peoples
    -1.23
     womens
    -0.93
     Womens
    -0.92
     childrens
    -0.91
     childs
    -0.87
     mans
    -0.87
     Peoples
    -0.83
    ones
    -0.83
     mens
    -0.82
     Indias
    -0.79
    POSITIVE LOGITS
    Décès
    0.44
    muo
    0.43
    CreateModel
    0.40
    ografija
    0.40
    addContainerGap
    0.40
    Clik
    0.40
    leswig
    0.39
    rafo
    0.38
     României
    0.38
     sanitarios
    0.37
    Activations Density 0.003%

    No Known Activations