© 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. 1-CLT-HP
    4. 454
    Prev
    Next
    INDEX
    Explanations

    serve

    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
    +#+
    -0.73
    Formazione
    -0.64
    Weblinks
    -0.64
    IBar
    -0.62
    DockStyle
    -0.60
    BagConstraints
    -0.60
     SafeMath
    -0.58
    ubri
    -0.58
     الدولى
    -0.57
    Autoritní
    -0.57
    POSITIVE LOGITS
     to
    0.49
     decision
    0.49
     all
    0.48
     "{{
    0.47
     pulito
    0.44
    enda
    0.44
     Hon
    0.44
    Hon
    0.43
    kanan
    0.43
    impresa
    0.43
    Activations Density 0.025%

    No Known Activations