© 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. 0-CLT-HP
    7. 93384
    Prev
    Next
    INDEX
    Explanations

    century

    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
     ujednoznacz
    -1.21
    RenderAtEndOf
    -1.19
    ScopeManager
    -1.16
     myſelf
    -1.14
    AddTagHelper
    -1.13
     itſelf
    -1.11
    ſelf
    -1.10
    ſelves
    -1.10
    NUMX
    -1.09
    ValueStyle
    -1.07
    POSITIVE LOGITS
    2
    0.80
    4
    0.79
    ,
    0.77
    1
    0.75
    3
    0.75
     [
    0.73
     with
    0.70
    5
    0.68
    .
    0.67
    7
    0.67
    Activations Density 0.162%

    No Known Activations