© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16113
    Prev
    Next
    INDEX
    Explanations

    electrical outlets and dates

    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
    Negative Logits
    으로
    -0.62
    jspx
    -0.55
    <bos>
    -0.52
     الاطلاع
    -0.51
     outlets
    -0.48
    seiti
    -0.46
    x
    -0.45
    ed
    -0.45
    es
    -0.44
    eser
    -0.42
    POSITIVE LOGITS
     lenker
    0.63
     Hebron
    0.60
     gynhyrchwyd
    0.60
     يتيمه
    0.59
     Arque
    0.59
     Aérea
    0.59
     giacca
    0.58
     jScrollPane
    0.58
    homonymie
    0.57
     behulp
    0.57
    Activations Density 0.021%

    No Known Activations