© 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. 0-RES-MATRYOSHKA-DC
    7. 11084
    Prev
    Next
    INDEX
    Explanations

    expressions of religious or spiritual beliefs about blending or reconciling different faiths

    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
     unknownFields
    -0.64
     BufferedWriter
    -0.61
    tagHelperRunner
    -0.59
    CommandText
    -0.56
    expandindo
    -0.55
    Jus
    -0.54
     Pard
    -0.53
     مشين
    -0.53
     Corners
    -0.52
    varargin
    -0.52
    POSITIVE LOGITS
    aking
    2.94
    aked
    2.03
    aker
    1.88
    AKING
    1.79
    akers
    1.52
    AKER
    1.34
    aken
    1.21
    akes
    1.20
    aky
    0.94
    AKES
    0.90
    Activations Density 0.001%

    No Known Activations