© 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. 11519
    Prev
    Next
    INDEX
    Explanations

    references to informational resources or FAQs

    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
    ंदीखरीदारी
    -0.85
    MessageOf
    -0.71
     لينك
    -0.70
    addPreferredGap
    -0.63
    GEBURTS
    -0.60
    IsContent
    -0.59
     CreateTagHelper
    -0.56
    nessione
    -0.52
    BindView
    -0.52
    aronne
    -0.52
    POSITIVE LOGITS
    faq
    3.19
     FAQ
    2.98
    FAQ
    2.89
    FAQs
    2.52
     FAQs
    2.41
     faq
    2.28
    faqs
    2.19
    Faq
    1.86
    Frequently
    1.81
     Frequently
    1.42
    Activations Density 0.000%

    No Known Activations