© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9248
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and computational steps within programming, particularly regarding strides and dimensions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    /*
    -0.64
    //*[@
    -0.54
     Klon
    -0.54
    fassungs
    -0.54
    elor
    -0.53
     Vols
    -0.52
    zzi
    -0.52
     Hathaway
    -0.52
    nå
    -0.52
    remont
    -0.51
    POSITIVE LOGITS
     stride
    1.61
    stride
    1.43
    Stride
    1.40
     strides
    1.16
    strides
    1.08
    licet
    0.86
    Carriera
    0.84
    ChildScrollView
    0.84
     MainAxisSize
    0.83
    ‍♂️
    0.79
    Activations Density 0.003%

    No Known Activations