© 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. 3945
    Prev
    Next
    INDEX
    Explanations

    the dependency on a specific parameter or variable

    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
     dependency
    -0.93
     Dependent
    -0.91
     dependent
    -0.90
    dependent
    -0.88
    Dependent
    -0.86
     dependence
    -0.85
     dependencies
    -0.84
     reliant
    -0.78
    dependence
    -0.74
     Dependence
    -0.72
    POSITIVE LOGITS
     depends
    1.79
     Depends
    1.66
    depends
    1.59
    Depends
    1.41
     dipende
    1.23
     depend
    1.10
     depended
    0.95
     zależy
    0.94
     depende
    0.82
     зависит
    0.78
    Activations Density 0.012%

    No Known Activations