© 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. 4-CLT-HP
    7. 2765
    Prev
    Next
    INDEX
    Explanations

    Programming/code context

    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
    oneofs
    -0.60
    Datuak
    -0.54
     mergeFrom
    -0.54
     resourceCulture
    -0.54
    WriteBarrier
    -0.53
     thyself
    -0.51
     *)__
    -0.51
    you
    -0.50
    ::~
    -0.49
    MessageState
    -0.49
    POSITIVE LOGITS
     Roskov
    0.62
    Tikang
    0.50
    ftagPool
    0.47
    empêcher
    0.45
    struzione
    0.45
    pande
    0.44
    tifact
    0.44
     acheteurs
    0.44
     nadie
    0.43
    RTHOOK
    0.43
    Activations Density 0.004%

    No Known Activations