© 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. 51
    Prev
    Next
    INDEX
    Explanations

    sections of formatted documents, particularly those with marked or symbolic annotations and structured layout elements

    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
    RouterModule
    -0.60
    gridx
    -0.59
     Rond
    -0.57
    ｜
    -0.56
     useSelector
    -0.55
     COB
    -0.54
    ագրություններ
    -0.54
     photolibrary
    -0.54
    ="$(
    -0.53
    /"+
    -0.53
    POSITIVE LOGITS
     *
    2.78
     **
    1.77
     *$
    1.75
     *
    1.72
     $*$
    1.70
     (*
    1.66
     *(
    1.63
     *\
    1.59
     *"
    1.59
     *,
    1.54
    Activations Density 3.036%

    No Known Activations