© 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. 13083
    Prev
    Next
    INDEX
    Explanations

    references to wired or wired-in electronic components or connections

    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
    yntaxException
    -0.59
    Portail
    -0.56
    IntoConstraints
    -0.55
    subplots
    -0.53
    󠁢
    -0.52
    imir
    -0.50
    oliber
    -0.49
    engagent
    -0.49
     destin
    -0.48
    FontOfSize
    -0.48
    POSITIVE LOGITS
     Tate
    0.87
    ]++;
    0.83
    idom
    0.83
    Tate
    0.82
     wired
    0.74
    adaptiveStyles
    0.73
     Wired
    0.69
    vice
    0.67
     Abbas
    0.65
    onto
    0.65
    Activations Density 0.084%

    No Known Activations