© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 498
    Prev
    Next
    INDEX
    Explanations

    places

    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
     компаний
    -0.49
    ₂)
    -0.47
     Colleges
    -0.45
     mark
    -0.45
    ibatis
    -0.45
    \}_{
    -0.44
    openzeppelin
    -0.44
    PageContext
    -0.44
     côtés
    -0.43
    __',
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.69
     ProtoMessage
    0.68
     الحره
    0.64
     BorderSide
    0.63
     gynhyrchwyd
    0.59
    kháu
    0.57
    +#+#
    0.57
    Hochspringen
    0.57
     BoxFit
    0.57
     ballots
    0.56
    Activations Density 0.016%

    No Known Activations