© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5604
    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
    \{\\
    -0.68
     that
    -0.63
     whereof
    -0.60
    ütfen
    -0.54
    isDebugEnabled
    -0.53
     they
    -0.51
     ClassNotFound
    -0.49
     those
    -0.49
     strtotime
    -0.49
     gammal
    -0.49
    POSITIVE LOGITS
     concern
    0.75
     thought
    0.64
     EconPapers
    0.63
    :✨
    0.62
     interest
    0.54
     worry
    0.53
     AssemblyCulture
    0.53
    concern
    0.53
    uidado
    0.52
     idea
    0.52
    Activations Density 0.002%

    No Known Activations