© 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. 3741
    Prev
    Next
    INDEX
    Explanations

    Emails and medical texts

    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
     שוליים
    -0.69
    tvguidetime
    -0.63
    Gambas
    -0.60
     estekak
    -0.57
     <<<<<<<<<<<<<<
    -0.56
    URUS
    -0.55
     Lur
    -0.54
    
    -0.53
     ligiloj
    -0.53
     Mero
    -0.52
    POSITIVE LOGITS
    Istorija
    0.65
    ReusableCell
    0.56
     commerciales
    0.53
     difficiles
    0.50
    uncher
    0.50
     utilizzati
    0.49
     européens
    0.49
     suivantes
    0.47
    migrationBuilder
    0.47
     useState
    0.46
    Activations Density 0.002%

    No Known Activations