© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1339
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
     vallée
    -0.47
     âgé
    -0.44
     allant
    -0.42
     endings
    -0.41
    first
    -0.41
    last
    -0.41
    Ends
    -0.40
     pozdě
    -0.40
    SizeMode
    -0.40
     prossima
    -0.40
    POSITIVE LOGITS
    __":
    0.75
     presentation
    0.67
    )}</
    0.65
     autorytatywna
    0.64
     column
    0.63
    Rüyada
    0.61
     session
    0.61
    SharedDtor
    0.60
    JspWriter
    0.60
    tagHelperRunner
    0.60
    Activations Density 0.005%

    No Known Activations