© 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. 43541
    Prev
    Next
    INDEX
    Explanations

    mitochondria

    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
     AssemblyCulture
    -1.23
     betweenstory
    -1.13
     myſelf
    -1.09
     fédé
    -1.06
     itſelf
    -1.05
    ñores
    -1.03
     anún
    -1.02
     Efq
    -1.02
     Monfieur
    -1.02
    ſelf
    -1.01
    POSITIVE LOGITS
     and
    0.75
     in
    0.68
     (
    0.65
     are
    0.62
     
    0.59
     end
    0.58
     or
    0.57
     en
    0.55
     con
    0.54
    ,
    0.53
    Activations Density 0.119%

    No Known Activations