© 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. 2-RES-MATRYOSHKA-DC
    7. 5400
    Prev
    Next
    INDEX
    Explanations

    references to relative file paths and includes in code snippets

    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
     scienza
    -0.60
     Kish
    -0.55
    kelen
    -0.54
     Kast
    -0.54
    Bik
    -0.53
    Gui
    -0.52
     KIR
    -0.51
    prost
    -0.50
    Quinn
    -0.50
     Fire
    -0.50
    POSITIVE LOGITS
    ="../
    2.50
     '../
    2.45
    ('../
    2.39
     "../
    2.38
    ("../
    2.31
     './
    1.95
     './../
    1.91
    ('./
    1.90
     "../../
    1.88
     '../../
    1.88
    Activations Density 0.011%

    No Known Activations