© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1821
    Prev
    Next
    INDEX
    Explanations

    regular

    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
     تضيفلها
    -0.76
     كومونز
    -0.71
     CreateTagHelper
    -0.68
    Искәрмәләр
    -0.67
    MessageOf
    -0.65
    клопе
    -0.65
    oplayer
    -0.63
     nahilalakip
    -0.63
    featureID
    -0.62
    webElementGuid
    -0.62
    POSITIVE LOGITS
    ctose
    0.45
    ontin
    0.44
     doce
    0.43
     unqualified
    0.43
     bas
    0.43
     computational
    0.43
    SWIG
    0.42
    Trained
    0.42
    gång
    0.42
     basic
    0.42
    Activations Density 0.005%

    No Known Activations