© 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. 5-CLT-HP
    7. 137
    Prev
    Next
    INDEX
    Explanations

    I

    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
    常
    -0.41
     cra
    -0.40
     Lord
    -0.39
     Clear
    -0.38
    ast
    -0.38
    stur
    -0.38
    στά
    -0.37
    Cra
    -0.37
    Rif
    -0.37
    mak
    -0.36
    POSITIVE LOGITS
     nahilalakip
    0.97
    AndEndTag
    0.97
    WebVitals
    0.94
     Италијани
    0.89
    цездатний
    0.87
    :+:
    0.79
    EDEFAULT
    0.78
     للاسماء
    0.77
    PreferredItem
    0.75
     MenuView
    0.75
    Activations Density 0.005%

    No Known Activations