© 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. 4-CLT-HP
    7. 1303
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    +#+#
    -0.67
    Демографія
    -0.62
     Our
    -0.56
    Chúng
    -0.52
     виправивши
    -0.50
     lenker
    -0.47
    сим
    -0.47
    Our
    -0.46
    enido
    -0.44
     doInBackground
    -0.44
    POSITIVE LOGITS
    __':
    0.69
     AssemblyTitle
    0.67
     your
    0.66
     Audiodateien
    0.65
     kanyang
    0.61
     ***!
    0.60
     CreateTagHelper
    0.60
     Ihrer
    0.59
    __':
    0.57
     '*')
    0.54
    Activations Density 0.007%

    No Known Activations