© 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. 4542
    Prev
    Next
    INDEX
    Explanations

    0

    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
     to
    -0.65
    0
    -0.61
    #+#
    -0.52
     -
    -0.48
    gemene
    -0.47
     –
    -0.47
     Berks
    -0.46
    ungkinan
    -0.45
     Pilih
    -0.45
    kyou
    -0.45
    POSITIVE LOGITS
     jenner
    0.57
     linkovi
    0.54
     TextAppearance
    0.53
     चीज़ों
    0.50
     مُعرِّف
    0.49
    awtextra
    0.49
    出版年
    0.47
    IsMutable
    0.47
    ={`/
    0.47
    reportWebVitals
    0.47
    Activations Density 0.002%

    No Known Activations