© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13718
    Prev
    Next
    INDEX
    Explanations

    references to textual citations or quotations

    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
     «
    -0.73
    \\
    -0.66
    \\\
    -0.65
     »
    -0.61
    </strong>
    -0.60
    »
    -0.59
    </h3>
    -0.58
    `
    -0.58
     tu
    -0.57
    」
    -0.56
    POSITIVE LOGITS
    ”)
    1.63
    ”),
    1.44
    ”).
    1.38
     Houſe
    1.22
    ’)
    1.21
     myſelf
    1.09
     Efq
    1.08
     Diſ
    1.05
     itſelf
    1.05
    ”!
    1.04
    Activations Density 0.006%

    No Known Activations