© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 366
    Prev
    Next
    INDEX
    Explanations

    Math problems

    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
    protoimpl
    -0.86
    DoubleQuotes
    -0.82
     autorytatywna
    -0.71
     متعلقه
    -0.70
    Autoritní
    -0.69
     winters
    -0.68
    Portály
    -0.68
     Italijanski
    -0.68
    发表于
    -0.68
     fewest
    -0.66
    POSITIVE LOGITS
     leaf
    0.41
     testigos
    0.40
    ande
    0.40
     folha
    0.39
     greater
    0.37
     niż
    0.37
    hagic
    0.37
    ook
    0.36
    ejs
    0.36
    Councillor
    0.36
    Activations Density 0.035%

    No Known Activations