© 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. 2-RES-MATRYOSHKA-DC
    7. 5188
    Prev
    Next
    INDEX
    Explanations

    references to methods or approaches for constructing orthogonal instruments

    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
     way
    -0.80
     BoxDecoration
    -0.67
    Autoritní
    -0.59
    ReusableCell
    -0.53
    Referencie
    -0.49
    Kjelder
    -0.49
    ConstraintMaker
    -0.49
    airro
    -0.47
     bao
    -0.46
    Whoever
    -0.46
    POSITIVE LOGITS
     ways
    2.59
     Ways
    2.39
     WAYS
    2.22
    Ways
    2.08
    ways
    1.51
    WAYS
    1.50
     maneras
    1.30
     maneiras
    1.26
     manières
    1.22
     façons
    1.00
    Activations Density 0.006%

    No Known Activations