© 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. 2-RES-MATRYOSHKA-DC
    7. 7517
    Prev
    Next
    INDEX
    Explanations

    references to branching points or the concept of branching

    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
    Negative Logits
     Gund
    -0.71
    IVEREF
    -0.64
    InteropServices
    -0.64
     effusion
    -0.63
    لاق
    -0.60
    oulos
    -0.60
    leun
    -0.57
    dirond
    -0.57
     Karls
    -0.57
    __":
    -0.57
    POSITIVE LOGITS
     branch
    3.48
     branches
    3.25
     Branch
    3.22
    branch
    3.16
    Branch
    3.09
     BRANCH
    3.05
     Branches
    2.94
    BRANCH
    2.83
    branches
    2.78
    Branches
    2.67
    Activations Density 0.010%

    No Known Activations