© 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. 1-CLT-HP
    7. 46145
    Prev
    Next
    INDEX
    Explanations

    the

    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
     ourselves
    -0.45
     متعلقه
    -0.42
     myself
    -0.41
    évaluateur
    -0.40
     Walkover
    -0.40
    \{\\
    -0.39
    openConnection
    -0.38
    Look
    -0.37
     विश्वसनीयता
    -0.37
     समीक्षाओं
    -0.36
    POSITIVE LOGITS
     &___
    0.68
    — 
    0.63
    runApp
    0.63
    extent
    0.62
     Faithful
    0.61
     executors
    0.61
     Keepers
    0.61
     '.')
    0.60
     custodi
    0.60
     Rector
    0.60
    Activations Density 0.016%

    No Known Activations