© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1472
    Prev
    Next
    INDEX
    Explanations

    library callouts and researcher names

    oai_token-act-pair · gemini-2.0-flash
    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
    fycat
    -0.79
     Cid
    -0.77
     Keller
    -0.77
    HttpFoundation
    -0.77
     Ese
    -0.74
    gäng
    -0.74
    ostock
    -0.71
     Pax
    -0.70
    iseaux
    -0.69
     Crosby
    -0.69
    POSITIVE LOGITS
    er
    1.08
     Josiah
    0.92
     Madsen
    0.91
     Valenzuela
    0.91
     FEC
    0.91
     UTA
    0.89
     COX
    0.83
     labourer
    0.83
     Boulogne
    0.82
     McE
    0.81
    Activations Density 6.667%

    No Known Activations