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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96143
    Prev
    Next
    INDEX
    Explanations

    to be

    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
     referrerpolicy
    -0.47
     ***!
    -0.41
     ""],
    -0.38
    hermes
    -0.38
    ということです
    -0.38
    alina
    -0.37
    led
    -0.37
    neux
    -0.37
     full
    -0.36
     бъдат
    -0.36
    POSITIVE LOGITS
     InputDecoration
    0.68
     AssemblyProduct
    0.68
    enumi
    0.67
    Дереккөздер
    0.67
    migrationBuilder
    0.67
    ergies
    0.66
     africaine
    0.64
    entiary
    0.61
    FundMe
    0.61
    ỡng
    0.60
    Activations Density 0.002%

    No Known Activations