© 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. 5-CLT-HP
    7. 125
    Prev
    Next
    INDEX
    Explanations

    Technical issues / bugs

    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
     or
    -0.45
    oxidase
    -0.40
     Kni
    -0.40
    IGraphics
    -0.40
    ähig
    -0.39
    נטרנט
    -0.39
    thenburg
    -0.37
    endfor
    -0.37
     Crete
    -0.36
    又は
    -0.36
    POSITIVE LOGITS
     дописавши
    0.86
     ErrIntOverflow
    0.73
     EconPapers
    0.71
    localctx
    0.70
     للمعارف
    0.69
     surla
    0.68
     Référence
    0.66
    OGND
    0.66
    GOTREF
    0.65
    Демографія
    0.62
    Activations Density 0.001%

    No Known Activations