© 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. 4328
    Prev
    Next
    INDEX
    Explanations

    lines of code related to importing modules or dependencies

    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
     Федерации
    -0.55
    ://
    -0.46
    ércoles
    -0.45
     flexível
    -0.45
    akun
    -0.44
     ajudá
    -0.44
    mmer
    -0.43
    ventude
    -0.42
     almofada
    -0.42
     biologique
    -0.42
    POSITIVE LOGITS
     import
    2.05
     Import
    1.21
    ::{
    1.06
     IMPORT
    1.05
     importing
    0.96
     imports
    0.92
     importation
    0.90
     importa
    0.88
     impor
    0.88
     importers
    0.85
    Activations Density 0.007%

    No Known Activations