© 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. 498
    Prev
    Next
    INDEX
    Explanations

    itself/themselves

    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
    WriteTagHelper
    -0.70
     cref
    -0.68
     own
    -0.61
    stående
    -0.56
     kohdetta
    -0.55
     Centr
    -0.53
     ThemeData
    -0.53
     egne
    -0.52
    isFunction
    -0.52
    jerc
    -0.51
    POSITIVE LOGITS
    protoimpl
    0.71
    sidemargin
    0.60
    tagHelperRunner
    0.58
    elemField
    0.56
     EconPapers
    0.52
    writeField
    0.51
    exitRule
    0.50
    localctx
    0.49
    PostInfinity
    0.49
     kaarangay
    0.48
    Activations Density 0.002%

    No Known Activations