© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    code

    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
    EMEN
    -0.52
     مز
    -0.50
     mì
    -0.48
     bender
    -0.48
    ην
    -0.48
    mande
    -0.47
    ன்
    -0.47
    acebook
    -0.47
     Mard
    -0.46
    MLLoader
    -0.46
    POSITIVE LOGITS
    WireFormat
    0.65
     resourceCulture
    0.59
    XmlType
    0.57
    Externé
    0.55
    Chham
    0.54
    EDEFAULT
    0.54
     تكبرها
    0.54
    sidemargin
    0.52
     réessayer
    0.52
    kadot
    0.51
    Activations Density 0.001%

    No Known Activations