© 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. 3829
    Prev
    Next
    INDEX
    Explanations

    references to the accuracy or quality of a reconstruction

    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
     metav
    -0.68
    PageModule
    -0.66
    Rüyada
    -0.62
     autorytatywna
    -0.60
     henvisninger
    -0.59
    estacks
    -0.59
     HasFactory
    -0.58
    toHaveBeenCalled
    -0.58
    YARD
    -0.57
     SDLK
    -0.56
    POSITIVE LOGITS
    integrity
    2.27
     integrity
    2.22
     Integrity
    2.03
     reconstruction
    1.99
     Reconstruction
    1.90
    Integrity
    1.80
     reconstruct
    1.73
    Reconstruction
    1.73
     reconstructed
    1.68
     reconstructions
    1.67
    Activations Density 0.084%

    No Known Activations