© 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. 12311
    Prev
    Next
    INDEX
    Explanations

    instances of specific code snippets or configuration patterns related to system setup and management

    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
    AndroidJUnit
    -0.72
    LEncoder
    -0.72
     Wikispecies
    -0.71
    pausal
    -0.69
     numerus
    -0.68
    MLLoader
    -0.66
     Infórmanos
    -0.64
    帖最后由
    -0.64
    AddHtmlAttribute
    -0.63
    InstanceState
    -0.63
    POSITIVE LOGITS
    
    0.72
    jsxFileName
    0.67
    ↵↵
    0.64
    </b>
    0.61
    ;">
    0.56
    '];?>
    0.55
    </strong>
    0.54
    üyada
    0.52
    ).
    0.51
     \
    0.49
    Activations Density 2.180%

    No Known Activations