© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13670
    Prev
    Next
    INDEX
    Explanations

    numerical expressions or values related to dosages, measurements, or calculations

    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
     Majefty
    -0.66
     Houſe
    -0.66
     UITableView
    -0.58
     militare
    -0.54
     Gonzalo
    -0.53
    )?;
    -0.51
     Sancho
    -0.50
    +:+
    -0.50
     Mongols
    -0.49
     Reſ
    -0.47
    POSITIVE LOGITS
     .\
    3.23
     CanadaChoose
    0.73
     ,\
    0.73
    posedge
    0.71
     виправивши
    0.67
    enswert
    0.67
     ./
    0.65
    HasForeignKey
    0.65
     "..\..\..\
    0.63
    httphttps
    0.63
    Activations Density 0.000%

    No Known Activations