© 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. 1-RES-MATRYOSHKA-DC
    7. 615
    Prev
    Next
    INDEX
    Explanations

    code snippets related to object-oriented class definitions and interface implementation

    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
     based
    -1.76
    Based
    -1.62
     Based
    -1.56
    based
    -1.47
     BASED
    -1.45
     berdasarkan
    -1.17
     depending
    -1.16
     basado
    -1.16
     basée
    -1.08
    BASED
    -1.06
    POSITIVE LOGITS
     base
    3.80
    base
    3.64
     Base
    3.56
    Base
    3.44
    BASE
    2.92
     BASE
    2.91
     bases
    2.28
     Bases
    2.16
    bases
    2.13
     getBase
    2.02
    Activations Density 0.481%

    No Known Activations