© 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. 2-RES-MATRYOSHKA-DC
    7. 4281
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "de" (likely "of" or "from" in various languages)

    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
    gespräch
    -0.44
     бюро
    -0.44
     fact
    -0.43
    fürst
    -0.42
    Abp
    -0.41
    letterSpacing
    -0.40
     Voiture
    -0.40
    رای
    -0.40
    seros
    -0.40
    gorm
    -0.40
    POSITIVE LOGITS
    de
    1.57
    ded
    1.34
    ding
    1.29
    di
    1.28
    des
    1.28
    din
    1.27
    der
    1.22
    dy
    1.18
    ders
    1.16
    den
    1.16
    Activations Density 0.289%

    No Known Activations