© 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. 24-RES-MATRYOSHKA-DC
    7. 26
    Prev
    Next
    INDEX
    Explanations

    statistics and data processing terminology involving matrices and transforms

    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.24.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.24.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
     sogni
    -0.67
     portata
    -0.66
     réfrig
    -0.64
     oreilles
    -0.63
     lèvres
    -0.63
     fieltro
    -0.62
     petto
    -0.61
     épaules
    -0.61
     pioggia
    -0.61
     belas
    -0.60
    POSITIVE LOGITS
     parameter
    0.82
     Gaussian
    0.77
     random
    0.74
     sampled
    0.73
     polynomial
    0.72
     averaged
    0.72
     $\
    0.71
     values
    0.69
     sampling
    0.69
     coefficients
    0.69
    Activations Density 16.337%

    No Known Activations