© 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. 0-CLT-HP
    7. 45574
    Prev
    Next
    INDEX
    Explanations

    {

    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
     noires
    -0.59
     fallu
    -0.57
    Queryable
    -0.54
     led
    -0.47
    Portale
    -0.47
     landen
    -0.47
     prosjek
    -0.47
    ManagedBean
    -0.47
     grig
    -0.47
    NonQuery
    -0.46
    POSITIVE LOGITS
    enumi
    0.69
    MigrationBuilder
    0.69
     المعيارى
    0.68
     الرياضيه
    0.68
    הערות
    0.65
    EndInit
    0.65
     continuant
    0.63
    Einzelnachweise
    0.62
    новниш
    0.62
    OGND
    0.62
    Activations Density 1.493%

    No Known Activations