© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44128
    Prev
    Next
    INDEX
    Explanations

    Hong Kong

    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
     Kong
    -0.98
    Kong
    -0.93
    IDA
    -0.90
     kong
    -0.77
    kong
    -0.71
     KONG
    -0.66
     presta
    -0.47
    SequentialGroup
    -0.46
    igenschaften
    -0.46
     secas
    -0.46
    POSITIVE LOGITS
    SCHEME
    0.67
     makeStyles
    0.61
    ynb
    0.59
     Doctrine
    0.57
    Citiți
    0.57
     Scheme
    0.57
     DBNull
    0.57
     BorderLayout
    0.55
     Crater
    0.55
    ::-
    0.55
    Activations Density 0.239%

    No Known Activations