© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    and

    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
     zelfs
    -0.59
    setVerticalGroup
    -0.59
     dessutom
    -0.55
     jopa
    -0.51
     oignons
    -0.50
    /#/
    -0.49
    áctenos
    -0.49
     Hence
    -0.48
    )<\
    -0.47
     Thus
    -0.47
    POSITIVE LOGITS
    ngdoc
    0.65
     Roskov
    0.63
     darken
    0.58
    upol
    0.55
     darkening
    0.55
    клопе
    0.52
     poisoned
    0.52
     eun
    0.52
     despo
    0.52
     bitter
    0.52
    Activations Density 0.002%

    No Known Activations