© 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. 11763
    Prev
    Next
    INDEX
    Explanations

    protection

    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
     būt
    -0.42
    .
    -0.40
     زده
    -0.40
    -
    -0.37
     has
    -0.37
    ↵↵
    -0.36
     veze
    -0.36
     ayant
    -0.35
     steder
    -0.35
     ponerse
    -0.35
    POSITIVE LOGITS
    RenderAtEndOf
    1.05
    ItemBackground
    0.96
    CloseOperation
    0.95
     Мексичка
    0.88
    AnchorStyles
    0.88
     <=",
    0.87
    PreferredItem
    0.85
     AssemblyCompany
    0.85
     AttributeSet
    0.84
    awtextra
    0.84
    Activations Density 0.008%

    No Known Activations