© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    scientific/mathematical text

    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
     respectivamente
    -0.86
     respectively
    -0.77
    énario
    -0.64
     respectivement
    -0.61
     alike
    -0.57
    respectively
    -0.55
    WebControls
    -0.55
     initComponents
    -0.52
     noqa
    -0.52
     therefor
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.87
    complexContent
    0.66
    fjspx
    0.60
    UnknownFieldSet
    0.59
     ligiloj
    0.56
     الرياضيه
    0.55
     snippetHide
    0.54
     kasarigan
    0.54
     useAppContext
    0.52
    NameInMap
    0.51
    Activations Density 0.060%

    No Known Activations