© 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. 5729
    Prev
    Next
    INDEX
    Explanations

    questions about the presence, correctness, or status of code or technical information

    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
     mariée
    -0.52
     culoare
    -0.52
     loue
    -0.52
     drep
    -0.52
    PickerController
    -0.52
     colorear
    -0.51
     acoper
    -0.51
     wensen
    -0.51
     soggior
    -0.50
     Marlin
    -0.50
    POSITIVE LOGITS
    %?
    0.80
    ?
    0.75
     ever
    0.72
    PerformLayout
    0.71
     ?$
    0.71
    SequentialGroup
    0.65
    ]?
    0.65
    ganet
    0.64
    
    0.63
    </thead>
    0.62
    Activations Density 0.163%

    No Known Activations