© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6311
    Prev
    Next
    INDEX
    Explanations

    meant

    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
    Negative Logits
     AssemblyCompany
    -0.63
    AsUp
    -0.61
     kasarigan
    -0.56
    neurs
    -0.56
    ритори
    -0.53
     ujednoznacz
    -0.53
     &___
    -0.52
     newOwner
    -0.52
     that
    -0.50
    äfts
    -0.50
    POSITIVE LOGITS
    meant
    0.64
     intended
    0.57
     meant
    0.57
     Deleting
    0.55
    ToRemove
    0.55
     intending
    0.54
    ंदीखरीदारी
    0.53
     streamed
    0.53
    ToDelete
    0.52
     recovered
    0.51
    Activations Density 0.002%

    No Known Activations