© 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. 2-RES-MATRYOSHKA-DC
    7. 3343
    Prev
    Next
    INDEX
    Explanations

    specific graph structures and their labeled components

    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
     Z
    -0.57
    <eos>
    -0.55
     z
    -0.54
     her
    -0.52
    er
    -0.52
     w
    -0.52
    JTextField
    -0.49
    =
    -0.48
     f
    -0.47
     De
    -0.45
    POSITIVE LOGITS
     purpoſe
    0.96
     uſed
    0.92
     myſelf
    0.91
     itſelf
    0.89
     Majefty
    0.88
     препратки
    0.88
     ſtre
    0.87
     houſe
    0.86
     Houſe
    0.86
     ſtate
    0.85
    Activations Density 2.392%

    No Known Activations