© 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. 20-CLT-HP
    7. 72725
    Prev
    Next
    INDEX
    Explanations

    olfactory

    np_max-act-logits · 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
     nahilalakip
    -0.83
    RegressionTest
    -0.77
    Ligações
    -0.75
     betweenstory
    -0.74
     دیکھیے
    -0.74
    expandindo
    -0.74
    JspWriter
    -0.72
    titleMargin
    -0.72
    Források
    -0.69
     సౌకర్య
    -0.68
    POSITIVE LOGITS
     che
    0.51
     OR
    0.50
     vom
    0.48
     Lokales
    0.47
     G
    0.42
    annica
    0.41
    BALL
    0.39
     كرة
    0.38
    odorant
    0.38
    SqlClient
    0.37
    Activations Density 0.002%

    No Known Activations