© 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. 14926
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and references to figures

    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
    tır
    -0.52
    }{$\
    -0.49
     rata
    -0.47
    titu
    -0.46
    secon
    -0.46
     le
    -0.46
    థ
    -0.46
    ysty
    -0.45
     mold
    -0.45
    いき
    -0.45
    POSITIVE LOGITS
     ProtoMessage
    0.98
     disambiguazione
    0.89
    ConstraintMaker
    0.88
     ligiloj
    0.86
    rungsseite
    0.81
     يتيمه
    0.80
     nahilalakip
    0.79
     CommonModule
    0.77
     betweenstory
    0.77
    fjspx
    0.76
    Activations Density 0.039%

    No Known Activations