© 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. 0-CLT-HP
    7. 43750
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical publications

    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
    GOTREF
    -1.08
    tagHelperRunner
    -1.00
     مشين
    -0.97
    ंदीखरीदारी
    -0.95
    AccessorTable
    -0.93
    цездатний
    -0.93
     transfieras
    -0.91
    ScopeManager
    -0.90
    ValueStyle
    -0.89
    NUMX
    -0.88
    POSITIVE LOGITS
    ிர
    0.53
     
    0.52
    щу
    0.51
     of
    0.50
    ela
    0.47
    igen
    0.47
     “
    0.47
    of
    0.47
     t
    0.46
     á
    0.46
    Activations Density 0.241%

    No Known Activations