© 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. 0-RES-MATRYOSHKA-DC
    7. 15045
    Prev
    Next
    INDEX
    Explanations

    the structure of block-diagonal matrices representing decomposed state spaces

    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
     Dim
    -1.40
    Dim
    -1.35
     dim
    -1.03
     Dimit
    -0.88
     DIM
    -0.79
     Dimin
    -0.79
    Portale
    -0.74
     dimming
    -0.70
     Dimitri
    -0.66
     numberOfRows
    -0.65
    POSITIVE LOGITS
    dim
    1.59
     nakalista
    0.57
     parlamentar
    0.52
    protoc
    0.51
    endphp
    0.50
    ığım
    0.50
     però
    0.48
    rangian
    0.48
    AsUp
    0.47
    StackNavigator
    0.47
    Activations Density 0.005%

    No Known Activations