© 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. 43502
    Prev
    Next
    INDEX
    Explanations

    merge

    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
     merging
    -1.14
     fusing
    -1.13
     vectorielles
    -1.06
     combining
    -1.01
     Combining
    -0.96
     complètes
    -0.93
     prisonniers
    -0.93
     prêtres
    -0.91
     fusión
    -0.91
     réunis
    -0.89
    POSITIVE LOGITS
    s
    0.68
    ing
    0.62
    ся
    0.60
     past
    0.56
    es
    0.54
    ose
    0.54
     in
    0.52
    om
    0.52
     the
    0.52
     it
    0.52
    Activations Density 0.050%

    No Known Activations