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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4050
    Prev
    Next
    INDEX
    Explanations

    Explaining or defining

    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
    ViewImports
    -0.90
     Мексичка
    -0.85
     ſtand
    -0.81
    mybatisplus
    -0.81
    MigrationBuilder
    -0.81
     Efq
    -0.80
    yntaxException
    -0.79
     houſe
    -0.79
     Theſe
    -0.78
    хьтан
    -0.78
    POSITIVE LOGITS
    ,
    0.57
    Sibling
    0.41
     mitosis
    0.39
    anadas
    0.38
    hecimento
    0.37
     kolor
    0.36
    zepine
    0.36
     prière
    0.36
    otonin
    0.35
     góc
    0.35
    Activations Density 0.001%

    No Known Activations