© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 242
    Prev
    Next
    INDEX
    Explanations

    references to medical studies or data related to pharmacological treatments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     later
    -0.41
    enumi
    -0.38
     hinges
    -0.37
    enumii
    -0.34
     surroundings
    -0.33
     times
    -0.32
     raised
    -0.32
     g
    -0.31
     innovations
    -0.31
     Vargas
    -0.31
    POSITIVE LOGITS
     Италијани
    0.84
     autorytatywna
    0.75
     Administrativna
    0.71
     nakalista
    0.65
    Personensuche
    0.63
     Normdatei
    0.61
    OGND
    0.61
     noDo
    0.60
    MockBean
    0.57
    Autoritní
    0.54
    Activations Density 1.720%

    No Known Activations