© 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. 5-CLT-HP
    7. 2014
    Prev
    Next
    INDEX
    Explanations

    Course

    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
    asker
    -0.60
    SuccessListener
    -0.52
    Spill
    -0.52
     referrerpolicy
    -0.50
    ">*
    -0.50
     TRADE
    -0.50
     moindre
    -0.48
     Tra
    -0.48
    QUID
    -0.47
     SCOPE
    -0.47
    POSITIVE LOGITS
    basicConfig
    0.80
     law
    0.62
    DockStyle
    0.60
     Мексичка
    0.59
    CopyWith
    0.58
    bootstrapcdn
    0.56
     ―――――
    0.56
     الحره
    0.56
    parsedMessage
    0.55
     lenker
    0.54
    Activations Density 0.000%

    No Known Activations