© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14364
    Prev
    Next
    INDEX
    Explanations

    mes

    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
    mes
    -0.89
    MES
    -0.66
     Mes
    -0.61
    ed
    -0.58
    Mes
    -0.54
    ing
    -0.52
    ey
    -0.50
    me
    -0.50
     mes
    -0.48
    emb
    -0.47
    POSITIVE LOGITS
     Cæsar
    0.74
     ſeveral
    0.72
     ujednoznacz
    0.71
     pleaſure
    0.70
     myſelf
    0.70
     itſelf
    0.69
    thâu
    0.69
     <>",
    0.68
     photolibrary
    0.68
    ือง
    0.68
    Activations Density 0.221%

    No Known Activations