© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13871
    Prev
    Next
    INDEX
    Explanations

    references to chemical or biological treatments for cancer, particularly interleukins and immunotherapies

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     considérons
    -0.51
     Biol
    -0.49
    mmate
    -0.46
    neous
    -0.45
    teln
    -0.45
    pezif
    -0.44
     FetchType
    -0.44
    cang
    -0.44
     Sekund
    -0.44
     Wicidata
    -0.44
    POSITIVE LOGITS
    usion
    3.50
    usions
    2.00
    USION
    1.45
    uding
    1.41
    uded
    1.31
     allusion
    1.08
     allude
    1.05
    usive
    1.03
    usión
    1.02
    usione
    1.01
    Activations Density 0.003%

    No Known Activations