© 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. 91856
    Prev
    Next
    INDEX
    Explanations

    or

    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
     שוליים
    -0.54
    Abr
    -0.52
    ArgumentParser
    -0.50
    openqa
    -0.48
     <<<<<<<<<<<<<<
    -0.46
    φάλ
    -0.46
     >=",
    -0.46
     BoxFit
    -0.43
    المشاركات
    -0.43
     htons
    -0.43
    POSITIVE LOGITS
     Die
    0.77
     Read
    0.71
     Donate
    0.68
     Subscribe
    0.67
     Share
    0.65
     Register
    0.63
     Delete
    0.63
     Download
    0.62
     Save
    0.62
     Join
    0.61
    Activations Density 0.002%

    No Known Activations