© 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. 562
    Prev
    Next
    INDEX
    Explanations

    references to rules, guidelines, or policies

    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
     BoxDecoration
    -0.67
    ValueStyle
    -0.66
     broadest
    -0.63
     widest
    -0.62
    WaitGroup
    -0.62
     فريبيس
    -0.62
     specificity
    -0.60
    specification
    -0.60
    ProgressHUD
    -0.59
    ougou
    -0.59
    POSITIVE LOGITS
     certain
    3.78
     Certain
    3.52
    certain
    3.52
    Certain
    3.41
     CERTAIN
    3.03
     certaine
    2.73
     ciertas
    2.47
     ciertos
    2.44
     certa
    2.17
     bepaalde
    1.98
    Activations Density 0.058%

    No Known Activations