© 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. 15996
    Prev
    Next
    INDEX
    Explanations

    growth factors

    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
    mobile
    -0.59
     يتيمه
    -0.52
    read
    -0.52
     mobile
    -0.52
    pf
    -0.50
     departament
    -0.49
    مصادر
    -0.49
     Audiodateien
    -0.49
    GraphicsUnit
    -0.49
    RegistryLite
    -0.48
    POSITIVE LOGITS
    AsUp
    0.63
     prioritise
    0.50
    dafx
    0.49
     bathe
    0.48
     requerido
    0.47
     autorytatywna
    0.47
    ību
    0.46
     OFDb
    0.45
     simulations
    0.44
     summarise
    0.44
    Activations Density 0.232%

    No Known Activations