© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    percent

    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
     Administrativna
    -0.55
     more
    -0.54
     easier
    -0.54
     healthier
    -0.53
     happier
    -0.53
    anzi
    -0.52
     deduction
    -0.51
    easier
    -0.50
     depress
    -0.50
     lesser
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.88
    +#+#
    0.63
     cherchés
    0.60
    providedIn
    0.60
    httphttps
    0.57
     amitié
    0.56
    Personensuche
    0.55
    EndGlobalSection
    0.54
    kháu
    0.53
    
    0.52
    Activations Density 0.009%

    No Known Activations