© 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. 612
    Prev
    Next
    INDEX
    Explanations

    technical phrases related to model derivation, estimation, and data analysis

    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
     base
    -2.88
     Base
    -2.73
    base
    -2.66
    Base
    -2.61
     BASE
    -2.28
    BASE
    -2.23
     bases
    -2.09
     Bases
    -1.98
    bases
    -1.80
     getBase
    -1.66
    POSITIVE LOGITS
     based
    2.41
    Based
    2.19
     Based
    2.17
    based
    2.03
     BASED
    2.02
    BASED
    1.63
     basado
    1.42
     basée
    1.37
     berdasarkan
    1.29
     basé
    1.27
    Activations Density 0.079%

    No Known Activations