© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39786
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ObjectContext
    -0.61
    Portail
    -0.52
     doInBackground
    -0.52
    CompilerServices
    -0.51
    QApplication
    -0.50
     houſe
    -0.50
     chariot
    -0.50
     adjournment
    -0.50
    :✨
    -0.50
     ftate
    -0.50
    POSITIVE LOGITS
    SequentialGroup
    0.67
    "])){
    0.67
    oppa
    0.63
    ()">
    0.60
    。</
    0.58
    )}>
    0.58
     }}"></
    0.57
    )$}
    0.57
    contentLoaded
    0.56
    )">
    0.55
    Activations Density 0.136%

    No Known Activations