© 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. 22-RES-MATRYOSHKA-DC
    7. 2594
    Prev
    Next
    INDEX
    Explanations

    references to patents or other published work

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invention
    -0.53
     Invention
    -0.52
     CreateTagHelper
    -0.52
     ویکی‌پدیا
    -0.50
     scope
    -0.50
     INVENTION
    -0.50
    Scope
    -0.50
    RegressionTest
    -0.50
    scope
    -0.49
    EndProject
    -0.49
    POSITIVE LOGITS
     US
    0.84
     U
    0.71
     Japanese
    0.69
     houſe
    0.68
     Canadian
    0.68
     United
    0.66
    US
    0.65
     British
    0.63
    ########.
    0.62
     correctes
    0.60
    Activations Density 0.097%

    No Known Activations