© 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. 12-RES-MATRYOSHKA-DC
    7. 15776
    Prev
    Next
    INDEX
    Explanations

    terms related to adjuvant therapies in cancer treatment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     himſelf
    -0.71
     Ichigo
    -0.71
     Monfieur
    -0.69
     Fürsten
    -0.69
     Sigism
    -0.68
     coû
    -0.67
     препратки
    -0.67
     Notting
    -0.66
    felf
    -0.63
     Carboniferous
    -0.63
    POSITIVE LOGITS
    juvant
    1.92
     adjuvant
    1.20
    vants
    1.02
     surla
    0.74
     Sol
    0.68
    发表于
    0.67
     suivant
    0.67
    RSpec
    0.63
    PMailer
    0.63
    MODO
    0.62
    Activations Density 0.001%

    No Known Activations