© 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. 4131
    Prev
    Next
    INDEX
    Explanations

    references to programming language constructs, data structures, or code elements

    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
     compartida
    -0.56
    ğraf
    -0.55
    jenigen
    -0.54
     structure
    -0.54
    oustic
    -0.54
    ticity
    -0.54
    一支
    -0.52
     açıklama
    -0.50
     TextInputType
    -0.49
    structure
    -0.48
    POSITIVE LOGITS
    enum
    3.39
     enum
    3.25
    Enum
    2.38
    ENUM
    2.33
     Enum
    2.19
     enums
    2.11
    enums
    2.06
     enumeration
    1.69
    Enums
    1.52
    EnumValue
    1.46
    Activations Density 0.009%

    No Known Activations