© 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. 18-RES-MATRYOSHKA-DC
    7. 479
    Prev
    Next
    INDEX
    Explanations

    references to figures, tables, and other supplementary materials in academic papers

    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.18.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.18.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
    npos
    -0.59
     dew
    -0.56
    zyn
    -0.52
     Și
    -0.51
    deleteById
    -0.50
     [_
    -0.46
     NRW
    -0.46
     atât
    -0.46
    paper
    -0.45
     liderança
    -0.43
    POSITIVE LOGITS
     Fig
    0.99
    Fig
    0.92
     Figure
    0.90
    Figure
    0.87
    Figs
    0.81
    Figures
    0.78
     Figures
    0.77
    FIGURE
    0.74
    igure
    0.74
     fig
    0.73
    Activations Density 0.578%

    No Known Activations