© 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. 95479
    Prev
    Next
    INDEX
    Explanations

    medical, biological terms

    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
     pleaſure
    -1.73
     myſelf
    -1.73
     itſelf
    -1.65
     purpoſe
    -1.61
     Monfieur
    -1.58
     ſtate
    -1.52
     houſe
    -1.50
     raiſ
    -1.49
     ſta
    -1.46
     ſche
    -1.45
    POSITIVE LOGITS
    ly
    0.49
    ally
    0.48
    nya
    0.47
    ation
    0.47
    als
    0.45
    ary
    0.44
     Ar
    0.42
    ons
    0.42
    sp
    0.42
     Bor
    0.41
    Activations Density 1.695%

    No Known Activations