© 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. 5-CLT-HP
    7. 93942
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     autant
    -0.49
    ardians
    -0.44
    嗯
    -0.40
     tulee
    -0.40
     Qualquer
    -0.40
     elämä
    -0.39
     péld
    -0.39
     ``
    -0.38
     käs
    -0.37
     consentimento
    -0.37
    POSITIVE LOGITS
    ImageContext
    0.96
    <bos>
    0.85
     BoxFit
    0.79
    PerformLayout
    0.78
    makeConstraints
    0.76
    FormTagHelper
    0.76
    ValueStyle
    0.75
    complexContent
    0.75
    хьтан
    0.73
     estekak
    0.73
    Activations Density 0.345%

    No Known Activations