© 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. 97313
    Prev
    Next
    INDEX
    Explanations

    Saturn

    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
     Saturn
    -0.98
    ulsions
    -0.84
     @{
    -0.58
    çar
    -0.52
    المناصب
    -0.52
    cellona
    -0.50
     capacités
    -0.45
    icksburg
    -0.45
     ***!
    -0.44
     vérit
    -0.44
    POSITIVE LOGITS
    i
    0.86
    e
    0.68
    OGND
    0.66
    o
    0.61
     elbows
    0.60
     manhood
    0.60
     nipples
    0.59
    aine
    0.56
     Senado
    0.56
     cilia
    0.56
    Activations Density 1.425%

    No Known Activations