© 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. 13410
    Prev
    Next
    INDEX
    Explanations

    every

    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
     présidenti
    -0.52
     typelib
    -0.47
     devenus
    -0.46
     présidentielle
    -0.46
     secondes
    -0.45
     étrangères
    -0.44
     saites
    -0.44
     hâte
    -0.43
     mergeFrom
    -0.43
     démocratie
    -0.43
    POSITIVE LOGITS
     numberWith
    0.57
     насељу
    0.57
    存于互联网档案馆
    0.57
    
    0.56
    NUMX
    0.56
    pagestyle
    0.56
    ]));
    0.55
    hisattva
    0.55
    Chham
    0.54
     regenerated
    0.54
    Activations Density 0.005%

    No Known Activations