© 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. 11764
    Prev
    Next
    INDEX
    Explanations

    specific numerical data, labels, or quantified information within texts

    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
     Савезне
    -0.68
     Meksiku
    -0.66
     eso
    -0.62
    ModelAttribute
    -0.59
     Isso
    -0.57
    Isso
    -0.56
    躇
    -0.56
    这一点
    -0.54
    +:+
    -0.54
     daarbij
    -0.53
    POSITIVE LOGITS
     deze
    2.50
     diese
    1.79
     Deze
    1.77
     Diese
    1.44
     denna
    1.39
    Deze
    1.38
    Diese
    1.37
     dieser
    1.28
     denne
    1.27
    diese
    0.95
    Activations Density 0.000%

    No Known Activations