© 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. 2-RES-MATRYOSHKA-DC
    7. 3774
    Prev
    Next
    INDEX
    Explanations

    references to data deserialization processes or specific technical procedures

    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
    djangoproject
    -0.80
    ReusableCell
    -0.75
    QMetaType
    -0.74
     MainAxisSize
    -0.71
    HomeAsUpEnabled
    -0.71
     religieuse
    -0.70
    󠁢
    -0.69
    Autoritní
    -0.68
     sauvages
    -0.66
    SpringRunner
    -0.61
    POSITIVE LOGITS
     Des
    3.52
     des
    3.42
    Des
    3.34
    des
    3.09
     DES
    2.89
    DES
    2.70
     Desmond
    1.69
     Desh
    1.62
     Desi
    1.52
     desp
    1.49
    Activations Density 0.038%

    No Known Activations