© 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. 40386
    Prev
    Next
    INDEX
    Explanations

    time

    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
     vectorielles
    -0.75
    InputBorder
    -0.75
     rése
    -0.74
     avancée
    -0.69
     berätt
    -0.69
     médicaux
    -0.69
     fédé
    -0.68
     المعيارى
    -0.68
     chré
    -0.68
    ientras
    -0.67
    POSITIVE LOGITS
    ...
    0.60
    WithIOException
    0.57
    ↵
    0.56
     [
    0.56
    <h1>
    0.55
    ↵↵
    0.54
    ​
    0.54
    .
    0.54
    ↵↵↵
    0.52
    >
    0.52
    Activations Density 1.553%

    No Known Activations