© 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. 1-CLT-HP
    7. 9291
    Prev
    Next
    INDEX
    Explanations

    continuous

    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
     battre
    -0.55
     MediatR
    -0.54
     rayures
    -0.51
     poursuite
    -0.50
    GRANTED
    -0.50
    følgelig
    -0.50
    paigns
    -0.49
     complètes
    -0.48
     russes
    -0.48
    nave
    -0.47
    POSITIVE LOGITS
    تقاوى
    0.66
     protoimpl
    0.65
     '\\;'
    0.61
     mortality
    0.60
    новниш
    0.59
    CppMethod
    0.58
     ComVisible
    0.57
     kasarigan
    0.57
     Biôgrafia
    0.56
    WebVitals
    0.56
    Activations Density 0.016%

    No Known Activations