© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    references to the concept of merging or bringing together multiple elements in a unified or combined manner

    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
     strto
    -0.56
    adoras
    -0.56
    otle
    -0.54
    ınt
    -0.53
    IBOutlet
    -0.52
     userManager
    -0.51
    DataURL
    -0.49
    bruch
    -0.48
    userdetails
    -0.48
    tableFuture
    -0.47
    POSITIVE LOGITS
     Unified
    3.22
     unified
    3.02
    Unified
    2.91
    unified
    2.84
     unify
    2.08
    UNIFIED
    2.00
     unification
    1.87
     unifying
    1.86
    统一
    1.29
    統一
    1.19
    Activations Density 0.001%

    No Known Activations