© 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. 197
    Prev
    Next
    INDEX
    Explanations

    presence of code snippets or programming syntax

    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
    ValueGenerated
    -0.61
    はじめに
    -0.55
    Portale
    -0.50
     <<<<<<<<<<<<<<
    -0.49
     fol
    -0.47
    ->___
    -0.47
    ->_
    -0.46
    Autoritní
    -0.46
    IsContent
    -0.46
    SBATCH
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.70
    protoimpl
    0.69
    +#+
    0.61
     МВД
    0.59
     SEDS
    0.59
     inplace
    0.58
    kháu
    0.57
    amoan
    0.57
     indisponible
    0.57
     Exteriores
    0.57
    Activations Density 1.026%

    No Known Activations