© 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. 77234
    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
    complexContent
    -0.79
     الرياضيه
    -0.67
     Italijanski
    -0.66
    utilisons
    -0.65
    BASEPATH
    -0.64
    Хьажоргаш
    -0.63
    tagHelperRunner
    -0.63
    فایل‌لار
    -0.61
    Have
    -0.60
     Have
    -0.60
    POSITIVE LOGITS
     surface
    0.49
     crop
    0.48
    DESCRIPTOR
    0.47
     prevail
    0.41
     Reifen
    0.41
    derung
    0.41
     pan
    0.40
    ględ
    0.40
    ardin
    0.40
    BorderFactory
    0.38
    Activations Density 0.005%

    No Known Activations