© 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. 76878
    Prev
    Next
    INDEX
    Explanations

    do

    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
    moveToFirst
    -0.57
    AdapterFactory
    -0.56
    DEE
    -0.52
     Ediciones
    -0.51
    rizona
    -0.50
    ellyn
    -0.48
     Entdecke
    -0.48
    
    -0.48
     Daya
    -0.47
     Valentín
    -0.45
    POSITIVE LOGITS
     do
    2.58
     doing
    1.97
    do
    1.72
     did
    1.66
     Do
    1.59
    doing
    1.58
    Doing
    1.57
     Doing
    1.55
    Do
    1.48
     does
    1.48
    Activations Density 0.043%

    No Known Activations