© 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. 0-CLT-HP
    7. 95683
    Prev
    Next
    INDEX
    Explanations

    place

    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
     place
    -1.99
    place
    -1.48
     lugar
    -1.27
     Place
    -1.19
     PLACE
    -1.18
     miejsce
    -1.14
    Place
    -1.13
     stedet
    -1.04
    endroit
    -1.01
    PLACE
    -0.96
    POSITIVE LOGITS
     drops
    0.53
     and
    0.46
     monopolies
    0.43
    cephala
    0.43
    i
    0.43
    back
    0.43
     couche
    0.42
     lassen
    0.42
     Invention
    0.42
    bos
    0.41
    Activations Density 0.025%

    No Known Activations