© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    references to specific numeric quantities, particularly the number thirty

    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
    Diweddarwch
    -0.85
    __":
    -0.82
    __':
    -0.80
     Orrell
    -0.79
     AssemblyCompany
    -0.78
    клопе
    -0.75
     informée
    -0.74
    URLException
    -0.73
    '])){
    -0.72
    __":
    -0.71
    POSITIVE LOGITS
     sixty
    2.28
     fifty
    2.23
     forty
    2.22
     thirty
    2.19
     seventy
    2.19
     eighty
    2.17
     twenty
    2.03
     ninety
    1.99
     Fifty
    1.99
     Forty
    1.95
    Activations Density 0.018%

    No Known Activations