© 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. 1-CLT-HP
    7. 9726
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and names

    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
     OnInit
    -0.50
    httphttps
    -0.48
    hacker
    -0.48
    jspx
    -0.48
    "}")
    -0.46
    tonsoft
    -0.45
    HOL
    -0.44
    rī
    -0.44
    ology
    -0.43
    addContainerGap
    -0.43
    POSITIVE LOGITS
    EndGlobalSection
    0.64
    __(/*!
    0.63
     disponibilités
    0.59
    :✨
    0.58
    yntaxException
    0.57
    mmate
    0.56
    تقاوى
    0.54
     FishBase
    0.53
    tadiene
    0.53
    Carriera
    0.53
    Activations Density 0.012%

    No Known Activations