© 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. 1957
    Prev
    Next
    INDEX
    Explanations

    fellow

    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
     belonged
    -0.99
    belong
    -0.95
     fellow
    -0.93
     belonging
    -0.90
     belong
    -0.90
     belongs
    -0.83
     appartiennent
    -0.77
     FELLOW
    -0.77
     guide
    -0.75
    Fellow
    -0.75
    POSITIVE LOGITS
    ly
    0.78
    ances
    0.65
     ExecuteAsync
    0.63
    twimg
    0.62
    BufferException
    0.60
     to
    0.57
    ely
    0.57
    TabIndex
    0.57
     consultato
    0.57
     propOrder
    0.57
    Activations Density 0.062%

    No Known Activations