© 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. 45584
    Prev
    Next
    INDEX
    Explanations

    caps

    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
    nium
    -0.69
    ي
    -0.57
    nél
    -0.56
     white
    -0.56
    gatan
    -0.54
    jsdelivr
    -0.54
     in
    -0.54
     Ku
    -0.52
    SpringRunner
    -0.50
    y
    -0.50
    POSITIVE LOGITS
    AccessorTable
    0.95
     referenties
    0.75
     Meksiku
    0.75
    expandindo
    0.75
     Shakspeare
    0.73
    izr
    0.69
     Friar
    0.69
     octaves
    0.68
     octave
    0.66
     perſon
    0.64
    Activations Density 0.173%

    No Known Activations