© 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. 1-CLT-HP
    7. 13467
    Prev
    Next
    INDEX
    Explanations

    Abbreviations and unusual capitalization

    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
     bezeichneter
    -0.68
     referenties
    -0.62
    ########.
    -0.62
    mybatisplus
    -0.62
    leyebilirsiniz
    -0.59
    titleMargin
    -0.59
    Rowan
    -0.59
    ⓧ
    -0.58
    gameserver
    -0.56
    NgModule
    -0.56
    POSITIVE LOGITS
     Round
    0.52
     Rec
    0.52
     Parad
    0.51
     Club
    0.50
     Rounds
    0.50
     Center
    0.48
    eter
    0.47
    umą
    0.47
    ksis
    0.47
    ardo
    0.47
    Activations Density 0.059%

    No Known Activations