© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    by

    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
     credited
    -0.54
     written
    -0.54
     another
    -0.50
     hand
    -0.50
    */,
    -0.49
     <<<<<<<<<<<<<<
    -0.49
     treating
    -0.49
     banane
    -0.48
     mandat
    -0.48
    ust
    -0.48
    POSITIVE LOGITS
     lenker
    0.79
    Viitteet
    0.64
     متعلقه
    0.60
    __":
    0.60
    Демографія
    0.59
    مصادر
    0.56
    Referanser
    0.55
     esternos
    0.54
     ddelweddau
    0.54
     autorytatywna
    0.52
    Activations Density 0.002%

    No Known Activations