© 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. 4-CLT-HP
    7. 506
    Prev
    Next
    INDEX
    Explanations

    direction

    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
     désolés
    -0.57
    loem
    -0.54
    BackStack
    -0.52
    AutoScaleMode
    -0.51
     yourself
    -0.50
     vPvB
    -0.50
     оригіналу
    -0.50
    ients
    -0.48
     ujednoznacz
    -0.48
     desto
    -0.46
    POSITIVE LOGITS
     découver
    0.71
     ouverts
    0.69
     traditionnels
    0.68
     חיצוניים
    0.67
     complètes
    0.67
     ouvertes
    0.65
     mélanger
    0.65
     nemlig
    0.63
     dizaines
    0.63
     peindre
    0.63
    Activations Density 0.005%

    No Known Activations