© 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. 4-CLT-HP
    4. 2536
    Prev
    Next
    INDEX
    Explanations

    articles, news, research

    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
    complexContent
    -0.84
    تقاوى
    -0.81
    はじめに
    -0.57
    Geplaatst
    -0.57
     solcher
    -0.57
    FontOfSize
    -0.51
     چنین
    -0.51
     */;
    -0.51
    CloseOperation
    -0.51
    `;
    
    -0.51
    POSITIVE LOGITS
     wives
    0.55
     totalité
    0.54
     Lloyd
    0.52
    帖最后由
    0.52
     the
    0.52
    aucune
    0.52
     spouses
    0.51
     sexes
    0.50
    AttributeSet
    0.50
     King
    0.49
    Activations Density 0.002%

    No Known Activations