© 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. 7221
    Prev
    Next
    INDEX
    Explanations

    structural elements related to graphs or diagrams, such as nodes, edges, and their connections

    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
    <bos>
    -0.58
    Referències
    -0.47
     africains
    -0.47
     gangen
    -0.44
     betweenstory
    -0.43
    ．
    -0.43
     étoit
    -0.42
     parlamentar
    -0.42
     directos
    -0.42
    aarrggbb
    -0.41
    POSITIVE LOGITS
    تقاوى
    0.84
    GraphicsUnit
    0.82
     سكانية
    0.79
    CloseOperation
    0.79
     незавершена
    0.76
    Tikang
    0.72
     AssemblyVersion
    0.71
    Aktualisiert
    0.69
    WriteTagHelper
    0.69
    期刊论文
    0.68
    Activations Density 0.749%

    No Known Activations