© 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. 1-RES-MATRYOSHKA-DC
    7. 91
    Prev
    Next
    INDEX
    Explanations

    expressions of nested parentheses

    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
     -
    -0.86
     I
    -0.85
     O
    -0.81
     —
    -0.81
     –
    -0.81
     (
    -0.80
     Se
    -0.79
     "
    -0.78
     in
    -0.76
     [
    -0.75
    POSITIVE LOGITS
    (
    2.66
     Monfieur
    1.62
    (\
    1.60
    (
    1.59
     Efq
    1.58
     purpoſe
    1.57
     Houſe
    1.52
     pleaſure
    1.51
     Majefty
    1.48
     greateſt
    1.47
    Activations Density 3.255%

    No Known Activations