© 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. 5-CLT-HP
    7. 98174
    Prev
    Next
    INDEX
    Explanations

    including involving

    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
    zdo
    -0.47
     república
    -0.45
    Рекоменду
    -0.43
     चीज़ों
    -0.43
    낼
    -0.41
    Applicants
    -0.41
     dommage
    -0.41
     revend
    -0.40
    στη
    -0.40
     Vendors
    -0.39
    POSITIVE LOGITS
     <>",
    0.87
     reviewing
    0.70
     analysing
    0.68
     NSCoder
    0.68
     analyzing
    0.65
     دیکھیے
    0.65
     LoggerFactory
    0.65
     iprot
    0.65
     assessing
    0.62
     evaluating
    0.61
    Activations Density 0.008%

    No Known Activations