© 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. 90978
    Prev
    Next
    INDEX
    Explanations

    searching

    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
    Sucesor
    -0.82
     AssemblyProduct
    -0.73
     EClass
    -0.68
    AndEndTag
    -0.67
    SuppressMessage
    -0.66
    AsUp
    -0.65
     propOrder
    -0.65
     NgModule
    -0.65
     porcentual
    -0.64
    principalColumn
    -0.63
    POSITIVE LOGITS
     buying
    0.58
     purchasing
    0.55
     deciding
    0.53
     choosing
    0.52
     shopping
    0.51
     thinking
    0.51
     wondering
    0.50
     questioning
    0.50
     selecting
    0.49
     re
    0.48
    Activations Density 0.006%

    No Known Activations