© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93272
    Prev
    Next
    INDEX
    Explanations

    words ending in suffixes

    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
     EconPapers
    -1.06
    webElementXpaths
    -1.00
     betweenstory
    -0.94
     Roskov
    -0.91
    WithIOException
    -0.91
    oredCriteria
    -0.91
    OGND
    -0.87
     nakalista
    -0.84
    +#+#
    -0.84
    原始内容存档于
    -0.83
    POSITIVE LOGITS
    ly
    0.44
     promotion
    0.39
    辺
    0.38
    Trit
    0.38
     Motor
    0.38
     party
    0.38
    Bank
    0.37
     Diman
    0.37
     Bank
    0.35
    pet
    0.34
    Activations Density 0.534%

    No Known Activations