© 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. 38685
    Prev
    Next
    INDEX
    Explanations

    occurrence

    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
     Occurrence
    -1.23
     avoient
    -1.22
     étoient
    -1.18
     fédé
    -1.16
     Occur
    -1.15
     feroit
    -1.13
     ainfi
    -1.13
    ьаж
    -1.09
    UserScript
    -1.09
     المعيارى
    -1.08
    POSITIVE LOGITS
     and
    0.83
     in
    0.74
    ,
    0.70
     a
    0.68
     for
    0.68
     “
    0.68
     
    0.65
     at
    0.64
     the
    0.63
     as
    0.63
    Activations Density 0.405%

    No Known Activations