© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43597
    Prev
    Next
    INDEX
    Explanations

    Sounds or altered words

    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
     Efq
    -1.15
     raiſ
    -1.11
     itſelf
    -1.09
     myſelf
    -0.98
     Monfieur
    -0.97
     deſt
    -0.94
     Mahomet
    -0.93
     Majefty
    -0.93
     Shakspeare
    -0.93
     Houſe
    -0.91
    POSITIVE LOGITS
     démocr
    0.79
     chré
    0.73
     tromper
    0.70
     stället
    0.64
     maux
    0.63
     rapides
    0.62
     rêves
    0.61
     commerciaux
    0.61
     chrétiens
    0.60
     périodes
    0.60
    Activations Density 0.044%

    No Known Activations