© 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. 5-CLT-HP
    7. 4286
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     departe
    -0.45
     Junto
    -0.40
    Blk
    -0.40
    mona
    -0.40
    erro
    -0.40
     Achievement
    -0.38
     Tent
    -0.38
     unblock
    -0.38
     út
    -0.38
    Trả
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.84
    GraphicsUnit
    0.80
     Roskov
    0.78
    mybatisplus
    0.72
     kasarigan
    0.69
     &___
    0.66
     Normdatei
    0.65
    :✨
    0.63
    PMailer
    0.63
    onViewCreated
    0.62
    Activations Density 0.001%

    No Known Activations