© 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. 5-CLT-HP
    7. 91115
    Prev
    Next
    INDEX
    Explanations

    routines or schedules

    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
    новништво
    -0.66
    WireFormatLite
    -0.60
     GoogleFonts
    -0.60
    省市镇
    -0.56
    новниш
    -0.55
     répondu
    -0.53
     يتيمه
    -0.53
     distinguer
    -0.52
     kaksi
    -0.50
    /***/
    -0.49
    POSITIVE LOGITS
     temperatures
    0.56
     weights
    0.54
     Neub
    0.54
     highs
    0.53
     counts
    0.51
    ForValue
    0.50
     Erz
    0.50
     weather
    0.50
    Autoritní
    0.50
     Bur
    0.49
    Activations Density 0.002%

    No Known Activations