© 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. 6949
    Prev
    Next
    INDEX
    Explanations

    references to legal subjectivity or legal matters

    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
     objects
    -1.80
    objects
    -1.66
     Objects
    -1.63
     object
    -1.62
     OBJECT
    -1.54
    object
    -1.52
    Objects
    -1.45
     Object
    -1.41
    Object
    -1.36
    OBJECT
    -1.34
    POSITIVE LOGITS
     subject
    2.17
    subject
    1.93
     Subject
    1.80
     SUBJECT
    1.63
    Subject
    1.59
     subjected
    1.27
     fubject
    1.19
    SUBJECT
    1.12
     sujeito
    0.94
     subjecting
    0.93
    Activations Density 0.014%

    No Known Activations