© 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. 4-CLT-HP
    7. 2277
    Prev
    Next
    INDEX
    Explanations

    s

    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
     own
    -0.69
     finest
    -0.53
    s
    -0.51
    ghijklmnop
    -0.51
     main
    -0.48
    æus
    -0.47
     usual
    -0.46
     official
    -0.46
    ])/
    -0.44
     personal
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.00
    UrlResolution
    0.85
     <=",
    0.78
    IMPORTED
    0.75
    ChildScrollView
    0.74
    IntoConstraints
    0.74
    +#+#
    0.73
     Normdatei
    0.72
    GOTREF
    0.69
     esternos
    0.69
    Activations Density 0.392%

    No Known Activations