© 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. 94478
    Prev
    Next
    INDEX
    Explanations

    activity

    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
    -0.59
     NSCoder
    -0.51
     bezeichneter
    -0.48
    PRNewswire
    -0.48
     münd
    -0.47
     Sutra
    -0.46
    */}
    -0.44
     activator
    -0.44
     Acti
    -0.44
     ModelRenderer
    -0.43
    POSITIVE LOGITS
     defaultstate
    0.80
     سكانية
    0.71
    WithIOException
    0.61
    ordning
    0.54
     OFDb
    0.54
    aság
    0.52
    исленность
    0.51
    ✨:
    0.51
    cellaneous
    0.50
    AISSEE
    0.50
    Activations Density 0.002%

    No Known Activations