© 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. 4-CLT-HP
    4. 2468
    Prev
    Next
    INDEX
    Explanations

    Common English function words

    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
     preferably
    -0.60
    acamata
    -0.59
     yolk
    -0.58
     ſhall
    -0.58
     appunto
    -0.57
    ParallelGroup
    -0.57
     herewith
    -0.57
     megane
    -0.57
     himſelf
    -0.56
     insofar
    -0.56
    POSITIVE LOGITS
     ExecuteAsync
    0.56
    <bos>
    0.52
     Kid
    0.43
     initComponents
    0.43
     Introducing
    0.43
     Advanced
    0.43
     AssemblyTitle
    0.42
     lalu
    0.42
     ‘
    0.41
    LLocation
    0.41
    Activations Density 0.003%

    No Known Activations