© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92918
    Prev
    Next
    INDEX
    Explanations

    full

    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
     étro
    -0.69
     quelcon
    -0.67
    full
    -0.62
     enfans
    -0.62
     volledige
    -0.60
     réservé
    -0.59
     avoient
    -0.59
     محفوظة
    -0.58
     full
    -0.58
     réussite
    -0.57
    POSITIVE LOGITS
     advantage
    0.80
    HtmlAttribute
    0.72
     rein
    0.58
    ConstraintMaker
    0.58
    SequentialGroup
    0.56
     use
    0.52
    advantage
    0.52
     Advantage
    0.50
    iprot
    0.50
    кура
    0.48
    Activations Density 0.007%

    No Known Activations