© 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. 38686
    Prev
    Next
    INDEX
    Explanations

    following

    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
    ConstraintMaker
    -0.52
     n
    -0.38
     etc
    -0.36
    /
    -0.36
     tkinter
    -0.35
     /
    -0.35
     viewDidLoad
    -0.34
     au
    -0.34
    makeText
    -0.33
    Pry
    -0.33
    POSITIVE LOGITS
    <bos>
    2.39
     Савезне
    0.94
     Monfieur
    0.92
     Theſe
    0.90
     Efq
    0.89
     Anſ
    0.88
     Jefus
    0.86
     itſelf
    0.86
     ſta
    0.85
    ^(@)
    0.85
    Activations Density 0.208%

    No Known Activations