© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38266
    Prev
    Next
    INDEX
    Explanations

    me

    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
    me
    -1.91
    ME
    -0.98
    par
    -0.74
    Me
    -0.74
    mec
    -0.66
    mea
    -0.65
    ме
    -0.65
    mely
    -0.61
    ative
    -0.59
    nos
    -0.54
    POSITIVE LOGITS
    ftagPool
    0.71
    HandlerContext
    0.61
     Савезне
    0.60
    cyklopedia
    0.57
    saraba
    0.55
    Pratique
    0.55
    NullException
    0.55
     McIntyre
    0.55
     MainAxisSize
    0.55
    uillez
    0.54
    Activations Density 0.054%

    No Known Activations