© 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. 90850
    Prev
    Next
    INDEX
    Explanations

    causation/origins

    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
     responsibility
    -0.84
     respon
    -0.74
     tank
    -0.67
     Responsibility
    -0.66
     Tank
    -0.64
     Respon
    -0.64
     TANK
    -0.59
     attributed
    -0.56
     aluminum
    -0.55
    WebElementEntity
    -0.54
    POSITIVE LOGITS
     debout
    0.64
    theless
    0.62
     Hanno
    0.60
     kaynağından
    0.59
    ſelves
    0.59
    〢
    0.58
    iest
    0.57
    ſelf
    0.57
     auffi
    0.57
    sto
    0.56
    Activations Density 0.195%

    No Known Activations