© 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. 40289
    Prev
    Next
    INDEX
    Explanations

    General purpose

    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
    waves
    -0.73
     Efq
    -0.71
     incendie
    -0.70
    verwijspagina
    -0.68
     AIAA
    -0.68
     fince
    -0.67
     AssemblyProduct
    -0.66
     scolaire
    -0.65
     fathoms
    -0.65
     knots
    -0.64
    POSITIVE LOGITS
    InitVars
    0.60
     a
    0.58
     ja
    0.51
    Krok
    0.50
    i
    0.49
     an
    0.49
     our
    0.48
     the
    0.48
    RequestQueue
    0.48
    PRNewswire
    0.48
    Activations Density 0.911%

    No Known Activations