© 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. 1-RES-MATRYOSHKA-DC
    7. 472
    Prev
    Next
    INDEX
    Explanations

    words emphasizing or starting explanations or conclusions

    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
     Monfieur
    -0.69
     Cæsar
    -0.65
     Anſ
    -0.65
     isKindOfClass
    -0.60
     Архів
    -0.58
     utafitiHapana
    -0.57
     Breton
    -0.57
    datap
    -0.57
     cartaz
    -0.56
    ſelves
    -0.56
    POSITIVE LOGITS
     so
    4.09
    so
    3.31
     So
    3.25
    So
    3.20
     SO
    2.69
    SO
    2.19
     så
    2.13
     sooo
    2.06
     sooooo
    2.05
     soooo
    2.02
    Activations Density 0.603%

    No Known Activations