© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    chiropractor, duo

    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
     Trio
    -0.62
    Trio
    -0.60
    مصادر
    -0.59
    illai
    -0.57
    ropods
    -0.54
     "..\..\..\
    -0.54
    tagHelperRunner
    -0.52
     Duo
    -0.51
    hoeddwyd
    -0.51
     trio
    -0.50
    POSITIVE LOGITS
    ţion
    0.54
     незавершена
    0.52
     Balk
    0.51
    ppard
    0.50
    names
    0.49
    AccessorTable
    0.48
    scribers
    0.48
     disordered
    0.48
     franc
    0.47
    مؤ
    0.47
    Activations Density 0.019%

    No Known Activations