© 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. 2742
    Prev
    Next
    INDEX
    Explanations

    references to specific structured sections or subsections, often indicated by headers beginning with "Th" followed by a number

    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
    pausal
    -0.77
     Tate
    -0.65
    })));
    -0.61
     ens
    -0.60
     zap
    -0.59
     AssemblyCulture
    -0.58
     tach
    -0.57
     Zucker
    -0.57
     CIT
    -0.57
     Tach
    -0.57
    POSITIVE LOGITS
     Th
    2.75
    Th
    2.56
     TH
    2.22
     th
    2.16
    TH
    1.69
     THR
    1.54
     thorium
    1.47
     thri
    1.38
     THI
    1.38
     Thr
    1.38
    Activations Density 0.149%

    No Known Activations