© 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. 0-CLT-HP
    7. 94625
    Prev
    Next
    INDEX
    Explanations

    showing/providing information

    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
     us
    -1.41
     me
    -1.35
    me
    -0.90
    us
    -0.87
    Me
    -0.76
     Us
    -0.74
     their
    -0.73
    Us
    -0.73
     ihre
    -0.73
    their
    -0.69
    POSITIVE LOGITS
    GraphicsUnit
    0.77
     you
    0.74
    you
    0.59
     Você
    0.57
    Становништво
    0.55
    :✨
    0.54
    אתה
    0.52
    ècie
    0.51
     demurrer
    0.51
    Você
    0.50
    Activations Density 0.344%

    No Known Activations