© 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. 1-CLT-HP
    7. 735
    Prev
    Next
    INDEX
    Explanations

    duodenum research texts

    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
    ThroughAttribute
    -0.77
    snippets
    -0.58
     Internazionale
    -0.57
    ționale
    -0.56
     initComponents
    -0.56
     työn
    -0.56
    openzeppelin
    -0.55
     دیکھیے
    -0.54
    oneofs
    -0.53
     onAnimation
    -0.52
    POSITIVE LOGITS
    deres
    0.51
     trend
    0.46
     Trend
    0.43
    alised
    0.43
    rer
    0.42
    sities
    0.41
    IDTH
    0.41
     erd
    0.41
     elit
    0.41
    vere
    0.41
    Activations Density 0.009%

    No Known Activations