© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Went
    -0.41
    em
    -0.41
    cus
    -0.41
     em
    -0.40
    went
    -0.40
     Went
    -0.40
    cited
    -0.39
    redi
    -0.39
    COMP
    -0.38
    loc
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    0.94
     disambiguazione
    0.85
    PerformLayout
    0.68
     encontraban
    0.66
    AddTagHelper
    0.66
    onViewCreated
    0.66
     ویکی‌پدی
    0.63
     saites
    0.63
    Бахар
    0.63
     ">=
    0.63
    Activations Density 0.001%

    No Known Activations