© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77229
    Prev
    Next
    INDEX
    Explanations

    images and rendering

    np_max-act-logits · 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
    +#+#
    -1.00
     تضيفلها
    -0.81
     afbeeldingen
    -0.75
     automatiques
    -0.75
    ########.
    -0.75
    ^(@)
    -0.74
     Majefty
    -0.72
     prescriptions
    -0.71
     verhalen
    -0.70
     cérémonie
    -0.69
    POSITIVE LOGITS
     model
    0.64
     recreation
    0.54
    netbeans
    0.48
     rendering
    0.47
    pov
    0.47
     replica
    0.47
     image
    0.45
    enden
    0.45
     view
    0.43
     Ä
    0.43
    Activations Density 0.000%

    No Known Activations