© 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. 72630
    Prev
    Next
    INDEX
    Explanations

    The

    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
     humanity
    -0.85
     mankind
    -0.75
     humankind
    -0.71
     humans
    -0.71
    клопе
    -0.65
     Humanity
    -0.59
    rawDesc
    -0.57
     manusia
    -0.57
     FetchType
    -0.57
     StatefulWidget
    -0.57
    POSITIVE LOGITS
     متعلقه
    0.71
     race
    0.54
    rinho
    0.54
    Chains
    0.52
     مشين
    0.52
     Race
    0.51
     being
    0.50
     MenuView
    0.50
    Logos
    0.50
    Editors
    0.49
    Activations Density 0.001%

    No Known Activations