© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    references to legal statutes, sections, and legal references

    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
     BrowserModule
    -0.99
    ModelSerializer
    -0.94
     configureStore
    -0.88
     MainAxisSize
    -0.87
    PerformLayout
    -0.85
    #+#
    -0.85
    IntoConstraints
    -0.84
    GOTREF
    -0.84
     propOrder
    -0.82
    Życiorys
    -0.81
    POSITIVE LOGITS
     Section
    0.67
    Section
    0.58
    lasz
    0.47
    werk
    0.43
     páss
    0.41
     متعلقه
    0.40
    PageNumber
    0.40
    сшта
    0.39
    İN
    0.39
     early
    0.38
    Activations Density 0.029%

    No Known Activations