© 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. 0-RES-MATRYOSHKA-DC
    7. 11635
    Prev
    Next
    INDEX
    Explanations

    the backward propagation signal

    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
     upward
    -1.02
     upwards
    -1.02
     downward
    -0.94
     downwards
    -0.88
     onwards
    -0.74
     onward
    -0.72
     inwards
    -0.61
    Incoming
    -0.55
     outwards
    -0.54
    outgoing
    -0.52
    POSITIVE LOGITS
     backward
    2.45
     Backward
    2.03
     backwards
    1.97
    backward
    1.88
    Backward
    1.51
    ArrowToggle
    0.89
     retrograde
    0.79
     defaultstate
    0.79
     AssemblyCulture
    0.78
    ंदीखरीदारी
    0.73
    Activations Density 0.001%

    No Known Activations