© 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. 13580
    Prev
    Next
    INDEX
    Explanations

    folder

    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
     folder
    -1.68
     Folder
    -1.64
    folder
    -1.48
     folders
    -1.39
    Folder
    -1.38
     Folders
    -1.24
    FOLDER
    -1.06
    文件夹
    -1.05
     Ordner
    -1.01
    folders
    -0.98
    POSITIVE LOGITS
    epam
    0.54
     abolished
    0.47
    theless
    0.44
    riles
    0.43
    onomics
    0.43
    isasi
    0.43
     MatDialog
    0.42
    science
    0.41
    erapeutics
    0.41
     entfer
    0.40
    Activations Density 0.010%

    No Known Activations