© 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. 1-RES-MATRYOSHKA-DC
    7. 760
    Prev
    Next
    INDEX
    Explanations

    phrases indicating destruction or destabilization

    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
    Autoritní
    -0.86
    QMetaType
    -0.67
    djangoproject
    -0.66
     fédé
    -0.66
     démocr
    -0.65
     eccl
    -0.63
     allemande
    -0.62
    tableFuture
    -0.59
     religieuse
    -0.57
    SpringRunner
    -0.57
    POSITIVE LOGITS
     des
    4.34
     Des
    3.95
    Des
    3.94
    des
    3.88
     DES
    3.42
    DES
    3.20
     Desh
    1.96
     Desmond
    1.78
     Desi
    1.71
     ihres
    1.68
    Activations Density 0.119%

    No Known Activations