© 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. 91074
    Prev
    Next
    INDEX
    Explanations

    health crisis

    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
     Италијани
    -0.89
    rungsseite
    -0.85
    Rüyada
    -0.82
     HasFactory
    -0.81
    ContentAlignment
    -0.81
    expandindo
    -0.80
     nakalista
    -0.80
    évaluateur
    -0.78
    AsUp
    -0.77
    SharedCtor
    -0.77
    POSITIVE LOGITS
    PHeader
    0.40
    ยาก
    0.39
    Zacks
    0.38
     meia
    0.36
     our
    0.36
    .=
    0.36
     threatening
    0.35
     daarna
    0.34
     hObject
    0.34
     Our
    0.33
    Activations Density 0.009%

    No Known Activations