© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    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
    Not in Any Lists

    No Comments

    Negative Logits
     precisione
    -0.55
     diversité
    -0.54
    Dar
    -0.50
     velocità
    -0.49
    ɜ
    -0.48
    over
    -0.45
    Württemberg
    -0.44
    RoleId
    -0.44
     déchets
    -0.44
    image
    -0.44
    POSITIVE LOGITS
    !*\
    0.69
     المعيارى
    0.64
     nahilalakip
    0.63
    StructEnd
    0.59
    NameInMap
    0.59
    httphttps
    0.59
    '):
    0.58
    ContentAsync
    0.57
    twimg
    0.57
     препратки
    0.57
    Activations Density 0.013%

    No Known Activations