© 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. 6289
    Prev
    Next
    INDEX
    Explanations

    references to religious faith, internal spiritual experiences, or significant life events

    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
     equipments
    -0.98
     advices
    -0.95
     Nowadays
    -0.95
     airc
    -0.82
     nowadays
    -0.80
    Nowadays
    -0.79
     firstly
    -0.75
     testimonies
    -0.75
     "..\..\
    -0.72
     researches
    -0.71
    POSITIVE LOGITS
    FWIW
    1.08
     ostensibly
    0.86
    issipp
    0.85
     disparate
    0.83
     conceivably
    0.82
    ].)
    0.81
     egregious
    0.80
    YMMV
    0.79
     increasingly
    0.79
     nominally
    0.79
    Activations Density 4.085%

    No Known Activations