© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40466
    Prev
    Next
    INDEX
    Explanations

    diabetic

    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
     Мексичка
    -0.96
     selling
    -0.95
     sell
    -0.94
     Selling
    -0.89
    IntoConstraints
    -0.88
     sells
    -0.85
     Sell
    -0.85
    Personendaten
    -0.84
    Sell
    -0.82
    Selling
    -0.80
    POSITIVE LOGITS
    delta
    0.46
    égard
    0.46
    pen
    0.43
    oghi
    0.42
    div
    0.42
    uchi
    0.42
     kohdetta
    0.42
    ñadir
    0.41
    gee
    0.41
     prest
    0.40
    Activations Density 1.449%

    No Known Activations