© 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. 731
    Prev
    Next
    INDEX
    Explanations

    people

    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
    staa
    -0.52
    orney
    -0.50
    cinoma
    -0.49
    Tav
    -0.48
    naught
    -0.47
     resourceCulture
    -0.46
    onucle
    -0.46
     conclure
    -0.46
    iolis
    -0.46
    منابع
    -0.46
    POSITIVE LOGITS
    <bos>
    1.03
    ConstraintMaker
    0.65
    execSQL
    0.60
    
    0.59
    AndEndTag
    0.58
    évaluateur
    0.55
    tanleria
    0.55
    ImageContext
    0.55
     للاسماء
    0.52
     Dubuque
    0.51
    Activations Density 0.101%

    No Known Activations