© 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. 1-CLT-HP
    7. 8634
    Prev
    Next
    INDEX
    Explanations

    image processing and phonetics

    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
    AndEndTag
    -0.82
    AndroidJUnit
    -0.73
     FetchType
    -0.73
    exitRule
    -0.66
    izability
    -0.65
    iastes
    -0.60
     enfans
    -0.60
     itſelf
    -0.60
     énergé
    -0.59
    otry
    -0.58
    POSITIVE LOGITS
     Louis
    0.50
     work
    0.49
    hexane
    0.49
     scale
    0.48
    loco
    0.47
     references
    0.47
    insatz
    0.46
    openConnection
    0.45
    marshaller
    0.45
     send
    0.45
    Activations Density 0.033%

    No Known Activations