© 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. 73126
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     חיצוניים
    -0.83
    interopRequire
    -0.81
    Hochspringen
    -0.72
    IUrlHelper
    -0.70
     onCreateView
    -0.69
    Datuak
    -0.69
    حياتها
    -0.68
    BeginInit
    -0.67
     utafitiHapana
    -0.67
     Answers
    -0.65
    POSITIVE LOGITS
     a
    0.63
     crossorigin
    0.44
     skry
    0.43
    <%@
    0.39
     an
    0.39
     ger
    0.37
    ever
    0.36
    UNTAIN
    0.35
    ci
    0.35
    Mammal
    0.35
    Activations Density 0.000%

    No Known Activations