© 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. 0-CLT-HP
    7. 38651
    Prev
    Next
    INDEX
    Explanations

    rough

    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
     rough
    -0.94
     Rough
    -0.93
    rough
    -0.92
    Rough
    -0.80
     solutions
    -0.74
     OnInit
    -0.73
     closer
    -0.66
     pleaſure
    -0.66
     løs
    -0.65
    таратура
    -0.64
    POSITIVE LOGITS
    AddTagHelper
    0.62
    s
    0.61
    WebElementEntity
    0.58
    er
    0.56
    drav
    0.54
    CreateMap
    0.54
    sos
    0.51
     Staf
    0.50
    TagHelpers
    0.48
    sx
    0.48
    Activations Density 0.045%

    No Known Activations