© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11845
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    inese
    -1.48
     eyelashes
    -0.66
     lashes
    -0.63
    mese
    -0.53
    HOP
    -0.50
    ope
    -0.49
     Chriſt
    -0.48
    onActivityResult
    -0.48
     BorderSide
    -0.47
     hops
    -0.47
    POSITIVE LOGITS
    MessageTagHelper
    0.58
    Билгалдахарш
    0.53
    Erreferentziak
    0.53
     Lan
    0.51
     vuitton
    0.49
     للاسماء
    0.48
    behörde
    0.48
    ClientSize
    0.48
     noDo
    0.48
     ivelany
    0.48
    Activations Density 0.010%

    No Known Activations