© 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. 6640
    Prev
    Next
    INDEX
    Explanations

    references to large quantities or numerical estimates

    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
     mergeFrom
    -0.69
    makeText
    -0.51
     @"/
    -0.51
    notated
    -0.50
    istoitu
    -0.49
    ContentAlignment
    -0.49
     liggen
    -0.49
    Eup
    -0.48
    Население
    -0.47
    mh
    -0.47
    POSITIVE LOGITS
     thousands
    2.56
     Thousands
    2.42
     hundreds
    2.39
    thousands
    2.39
    Thousands
    2.33
    hundreds
    2.25
     Hundreds
    2.23
    Hundreds
    2.19
     millions
    2.09
     tens
    2.08
    Activations Density 0.013%

    No Known Activations