© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41114
    Prev
    Next
    INDEX
    Explanations

    purification

    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
     Мексичка
    -0.77
     greater
    -0.73
     unified
    -0.69
    greater
    -0.68
    IANGLES
    -0.68
    flour
    -0.62
     radiation
    -0.61
     purified
    -0.59
     ControllerBase
    -0.58
     Radiation
    -0.58
    POSITIVE LOGITS
    fjspx
    0.68
     propOrder
    0.54
     straits
    0.52
     knowledge
    0.51
    ValueGeneration
    0.49
    isn
    0.49
     leider
    0.48
     encounter
    0.48
     onFailure
    0.48
    Illegal
    0.47
    Activations Density 0.190%

    No Known Activations