© 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. 40196
    Prev
    Next
    INDEX
    Explanations

    current events

    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
    OGND
    -0.74
    Bibliograf
    -0.70
     CreateTagHelper
    -0.62
     mắn
    -0.60
    èdia
    -0.59
    󠁮
    -0.59
    Portale
    -0.58
     iſt
    -0.58
     Dreyfus
    -0.58
     دیکھیے
    -0.57
    POSITIVE LOGITS
    SaveChangesAsync
    0.67
    UnsafeEnabled
    0.56
    akim
    0.48
    IsContent
    0.47
     wicker
    0.44
     abgerufen
    0.43
     smlou
    0.43
     nonUne
    0.43
     disposição
    0.43
     côtes
    0.42
    Activations Density 2.054%

    No Known Activations