© 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. 4-CLT-HP
    7. 5018
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     voks
    -0.54
     tartalomajánló
    -0.54
     vocales
    -0.50
    nyder
    -0.50
     courants
    -0.49
    tamanya
    -0.49
    queles
    -0.49
     supérieurs
    -0.49
     dernières
    -0.49
     amitié
    -0.48
    POSITIVE LOGITS
     Normdatei
    0.57
     mantel
    0.56
     Hait
    0.54
     Dartmouth
    0.53
     house
    0.52
     dorm
    0.52
     haus
    0.52
    ngdoc
    0.52
     itſelf
    0.52
     MTB
    0.51
    Activations Density 0.018%

    No Known Activations