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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13960
    Prev
    Next
    INDEX
    Explanations

    in

    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
     viewType
    -0.62
    cydow
    -0.59
    postIndex
    -0.56
    ัพท์
    -0.50
    EventQueue
    -0.49
    drawRect
    -0.49
     lccn
    -0.48
    uoš
    -0.47
     Walkover
    -0.47
    бва
    -0.46
    POSITIVE LOGITS
    stateMutability
    0.79
    تقاوى
    0.73
    ########.
    0.64
     يتيمه
    0.64
    astify
    0.62
     autorytatywna
    0.57
    RenderAtEndOf
    0.55
     елның
    0.54
    izr
    0.54
    GeneratedCode
    0.53
    Activations Density 0.003%

    No Known Activations