© 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. 1619
    Prev
    Next
    INDEX
    Explanations

    science

    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
    цездатний
    -1.05
    MigrationBuilder
    -1.03
    TagHelper
    -0.96
     GenerationType
    -0.92
     nahilalakip
    -0.92
     lump
    -0.90
    tagHelperRunner
    -0.90
     AssemblyProduct
    -0.83
    lump
    -0.83
     سكانية
    -0.82
    POSITIVE LOGITS
    ic
    0.61
    ed
    0.60
    ored
    0.48
    ir
    0.46
    eds
    0.46
    ers
    0.46
    id
    0.43
    od
    0.43
    ted
    0.43
    back
    0.43
    Activations Density 0.056%

    No Known Activations