© 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. 6216
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    bardier
    -0.48
    bewerken
    -0.45
     Quakers
    -0.44
    Історія
    -0.44
    CORBA
    -0.44
     Egyptians
    -0.44
     Conditions
    -0.44
     Hinduism
    -0.43
     Mexicans
    -0.43
     Bruno
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.71
     MainAxisSize
    0.70
    BeginContext
    0.68
    HasForeignKey
    0.68
    WriteBarrier
    0.67
     Tampoco
    0.64
    tvguidetime
    0.64
    AndEndTag
    0.63
    AlterField
    0.61
    =#{
    0.61
    Activations Density 0.003%

    No Known Activations