© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    ard

    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
     дописавши
    -0.56
    المناصب
    -0.52
    NegativeButton
    -0.51
    AddTagHelper
    -0.50
    <bos>
    -0.49
     بدر
    -0.45
    )))
    -0.44
    }*/
    -0.44
    CardHeader
    -0.44
     estekak
    -0.43
    POSITIVE LOGITS
    ViewImports
    0.58
     purpoſe
    0.57
     actionMode
    0.57
     airport
    0.57
    AutoField
    0.56
    gameserver
    0.56
     airfield
    0.56
     Efq
    0.54
     themſelves
    0.54
     Airport
    0.53
    Activations Density 0.004%

    No Known Activations