© 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. 1844
    Prev
    Next
    INDEX
    Explanations

    s

    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
    <bos>
    -0.93
     giustizia
    -0.82
    fjspx
    -0.81
    tagHelperRunner
    -0.80
     propOrder
    -0.75
     autorytatywna
    -0.74
     cherchés
    -0.74
     fieldNum
    -0.73
     démocr
    -0.71
    setVerticalGroup
    -0.70
    POSITIVE LOGITS
     physiological
    0.55
     total
    0.54
     mode
    0.54
     functional
    0.53
     full
    0.53
     natural
    0.52
     mean
    0.52
     average
    0.52
     digital
    0.50
     set
    0.48
    Activations Density 0.033%

    No Known Activations