© 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. 4272
    Prev
    Next
    INDEX
    Explanations

    references to the concept of forward propagation or forwarding in computational processes

    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
    +#+#
    -0.90
     Fron
    -0.87
    aarrggbb
    -0.87
     SqlConnection
    -0.86
    FormTagHelper
    -0.82
    ulemon
    -0.82
    XmlAccessType
    -0.82
    tagext
    -0.82
     nargin
    -0.81
     fron
    -0.81
    POSITIVE LOGITS
     forward
    3.52
    Forward
    3.22
     Forward
    3.22
    forward
    3.11
     FORWARD
    2.98
    FORWARD
    2.56
     forwards
    2.55
     forwarding
    2.03
     fwd
    1.95
     fow
    1.67
    Activations Density 0.028%

    No Known Activations