© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs

    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
     •
    -0.66
    hdashline
    -0.60
     home
    -0.59
    falgar
    -0.55
     Home
    -0.55
     -
    -0.54
    CALLBACK
    -0.53
    руется
    -0.52
     ?
    -0.51
     auto
    -0.51
    POSITIVE LOGITS
    HtmlAttribute
    0.95
    Зноскі
    0.94
     '\\;'
    0.85
    IVEREF
    0.85
    +#+#
    0.85
     Efq
    0.79
    ViewFeatures
    0.79
     doubtnut
    0.79
     myſelf
    0.78
     ་་
    0.77
    Activations Density 0.098%

    No Known Activations