© 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. 41040
    Prev
    Next
    INDEX
    Explanations

    horseback

    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
     médec
    -0.57
     enfans
    -0.56
     sembler
    -0.54
     fédé
    -0.52
     katun
    -0.51
     appliquer
    -0.51
    ligg
    -0.51
     különböz
    -0.51
     préoccup
    -0.50
     boî
    -0.50
    POSITIVE LOGITS
    ValueStyle
    0.96
    Personensuche
    0.95
    +#+#
    0.82
    EDEFAULT
    0.81
    DoubleQuotes
    0.80
     autorytatywna
    0.78
    Życiorys
    0.77
     resourceCulture
    0.74
    elemField
    0.71
    tagHelperRunner
    0.71
    Activations Density 0.143%

    No Known Activations