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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10824
    Prev
    Next
    INDEX
    Explanations

    references to the word "smokers" or related terminology

    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
     cer
    -0.64
     Cer
    -0.62
    Cer
    -0.61
    bentar
    -0.57
     intermittent
    -0.54
    ibrill
    -0.52
    abancı
    -0.52
    ждународ
    -0.52
    ereich
    -0.52
    verson
    -0.51
    POSITIVE LOGITS
    cers
    1.03
    ään
    0.99
     ELF
    0.86
    να
    0.84
     تضيفلها
    0.71
     nahilalakip
    0.68
    __*/
    0.68
    kers
    0.63
    νας
    0.61
     arşivlendi
    0.60
    Activations Density 0.002%

    No Known Activations