© 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. 318
    Prev
    Next
    INDEX
    Explanations

    4

    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
    ANTLR
    -0.44
    her
    -0.43
    PhysRevLett
    -0.41
    x
    -0.41
     Vergangenheit
    -0.41
    qrt
    -0.41
    once
    -0.40
     runs
    -0.39
    vaders
    -0.38
     aids
    -0.38
    POSITIVE LOGITS
     propOrder
    0.77
     AssemblyCompany
    0.71
    IntoConstraints
    0.69
    esgue
    0.69
     يتيمه
    0.68
    Hentet
    0.68
     autorytatywna
    0.68
     CreateTagHelper
    0.66
    tvguidetime
    0.66
    BoxShadow
    0.64
    Activations Density 0.001%

    No Known Activations