© 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. 90918
    Prev
    Next
    INDEX
    Explanations

    code

    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
    opan
    -2.73
    }{|
    -0.51
    MENAFN
    -0.47
    himovic
    -0.44
    MergeFrom
    -0.43
    ทร
    -0.40
    läufig
    -0.40
     má
    -0.39
    gia
    -0.39
     res
    -0.39
    POSITIVE LOGITS
     Infórmanos
    0.78
     المعيارى
    0.77
    ſelf
    0.76
    :✨
    0.74
     quæ
    0.74
     contextLoads
    0.73
     themſelves
    0.73
    ViewFeatures
    0.73
    QMetaType
    0.72
    tagHelperRunner
    0.69
    Activations Density 0.152%

    No Known Activations