© 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. 0-CLT-HP
    7. 90635
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
     émissions
    -0.60
    ally
    -0.59
     lèvres
    -0.58
    isuus
    -0.53
     collègues
    -0.53
    anía
    -0.53
    withstanding
    -0.52
     ogóle
    -0.52
    almente
    -0.52
     genoux
    -0.52
    POSITIVE LOGITS
     nahilalakip
    0.70
     للاسماء
    0.70
    Спољашње
    0.66
    akaian
    0.65
    WithIOException
    0.65
     genders
    0.63
     Italijanski
    0.62
    GEBURTSDATUM
    0.62
     costumes
    0.61
     estimés
    0.61
    Activations Density 0.109%

    No Known Activations