© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    campus, colleges, universities Method: 1, the most common and related tokens in MAX_ACTIVATING_TOKENS explanation: campus/colleges

    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
     dry
    -1.16
     sèche
    -1.05
    college
    -1.03
     dried
    -1.02
     dries
    -1.02
    dried
    -1.01
     sécher
    -0.98
    diagnosis
    -0.95
     CAMPUS
    -0.95
    dry
    -0.93
    POSITIVE LOGITS
     and
    0.59
    ↵↵
    0.55
     from
    0.52
    .
    0.49
    ↵
    0.49
     based
    0.48
     to
    0.48
     (
    0.48
     that
    0.45
     out
    0.45
    Activations Density 0.760%

    No Known Activations