© 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. 0-CLT-HP
    7. 1659
    Prev
    Next
    INDEX
    Explanations

    SSL

    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
     étoient
    -0.94
     avoient
    -0.91
     étoit
    -0.85
    ing
    -0.80
     feroit
    -0.80
     plufieurs
    -0.80
     pouvoit
    -0.79
     سكانية
    -0.78
     tasche
    -0.78
    dflare
    -0.77
    POSITIVE LOGITS
     in
    0.65
     pres
    0.63
     pret
    0.61
     as
    0.59
     Dem
    0.59
     demand
    0.59
    iewicz
    0.58
     and
    0.57
    lesia
    0.57
     sw
    0.57
    Activations Density 1.472%

    No Known Activations