© 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. 0-CLT-HP
    7. 97228
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    年
    -1.51
    年の
    -0.81
     年
    -0.77
    月
    -0.71
    年的
    -0.66
    年に
    -0.66
    ly
    -0.62
    년
    -0.61
    の
    -0.58
    年は
    -0.57
    POSITIVE LOGITS
    WriteBarrier
    0.62
     Мексичка
    0.62
    ⓧ
    0.60
     Dage
    0.60
     Visited
    0.60
     KERN
    0.57
    archiviato
    0.57
     Stationary
    0.57
     للمعارف
    0.57
     ICommand
    0.57
    Activations Density 1.678%

    No Known Activations