© 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. 24-RES-MATRYOSHKA-DC
    7. 839
    Prev
    Next
    INDEX
    Explanations

    words involved with mechanical systems and patents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.53
     BigInt
    -0.48
    ]--;
    -0.47
    glGen
    -0.46
    Stal
    -0.46
    BarStyle
    -0.44
     crossorigin
    -0.44
    writeField
    -0.43
     typedef
    -0.43
     substrate
    -0.43
    POSITIVE LOGITS
     manual
    0.97
     operation
    0.94
     operate
    0.94
     manually
    0.94
     operated
    0.93
     operator
    0.88
    操作
    0.88
     Manually
    0.87
     操作
    0.86
     switches
    0.85
    Activations Density 1.564%

    No Known Activations