© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2649
    Prev
    Next
    INDEX
    Explanations

    definition of words/commands

    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
     continuant
    -0.72
     Paglinawan
    -0.70
    Cyfeiriadau
    -0.69
    ंदीखरीदारी
    -0.66
    Jegyzetek
    -0.64
    
    -0.63
    MessageState
    -0.60
    StoryboardSegue
    -0.60
    tvguidetime
    -0.58
     Италијани
    -0.58
    POSITIVE LOGITS
     Assigned
    0.49
     monotony
    0.48
     captivity
    0.48
     sterility
    0.48
     Symmetry
    0.47
     Probable
    0.47
     especias
    0.47
    Rptr
    0.46
     loopholes
    0.46
     Gregorian
    0.46
    Activations Density 0.031%

    No Known Activations