© 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. 97284
    Prev
    Next
    INDEX
    Explanations

    valuation or biotechnology

    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
     myſelf
    -1.16
     itſelf
    -1.07
     Monfieur
    -1.07
    featureID
    -1.06
     houſe
    -1.06
     Majefty
    -1.06
     raiſ
    -1.03
     Efq
    -1.03
     Jefus
    -1.02
     uſed
    -1.02
    POSITIVE LOGITS
    m
    0.61
    n
    0.59
    am
    0.59
    he
    0.57
    nu
    0.52
    ua
    0.52
     <
    0.52
    c
    0.52
    ter
    0.51
     (
    0.50
    Activations Density 1.597%

    No Known Activations