© 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. 1-CLT-HP
    7. 11951
    Prev
    Next
    INDEX
    Explanations

    system, power, energy

    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
     насељу
    -0.63
     douleurs
    -0.60
    MigrationBuilder
    -0.57
    HtmlAttribute
    -0.54
     maggior
    -0.49
     économies
    -0.48
     trasmissione
    -0.48
     nyom
    -0.48
     difficulté
    -0.48
     gambe
    -0.47
    POSITIVE LOGITS
    Datuak
    0.69
    AccessorTable
    0.65
     createState
    0.61
     Rosetta
    0.61
     FishBase
    0.56
     sper
    0.56
     виправивши
    0.56
     Esperanto
    0.56
    isms
    0.56
     ComVisible
    0.55
    Activations Density 0.087%

    No Known Activations