© 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. 5-CLT-HP
    7. 94496
    Prev
    Next
    INDEX
    Explanations

    of

    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
     the
    -0.70
    principalColumn
    -0.66
    ніципалі
    -0.63
     "..\..\
    -0.62
     चीज़ों
    -0.52
     Cults
    -0.52
     COMPR
    -0.50
     propOrder
    -0.50
     who
    -0.49
     Meksiku
    -0.49
    POSITIVE LOGITS
     extranjera
    0.52
     Houſe
    0.52
    󠁴
    0.51
    course
    0.50
     getProperty
    0.49
    MessageWindow
    0.49
     lisäksi
    0.48
     peruana
    0.48
     incomplète
    0.48
    taste
    0.48
    Activations Density 0.004%

    No Known Activations