© 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. 12-RES-MATRYOSHKA-DC
    7. 14701
    Prev
    Next
    INDEX
    Explanations

    technical jargon or terms related to robotics and control systems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    kheim
    -0.66
     Felsen
    -0.54
    otides
    -0.52
    fileSize
    -0.52
    gdala
    -0.52
     calendriers
    -0.52
    esgue
    -0.51
    rrggbb
    -0.51
     dip
    -0.50
    prits
    -0.50
    POSITIVE LOGITS
     MonoBehaviour
    0.77
     Robotics
    0.73
    jsdelivr
    0.66
    makedirs
    0.63
    getMenuInflater
    0.63
     robotics
    0.62
    Digitized
    0.62
     Robots
    0.62
     locomotion
    0.61
     robot
    0.60
    Activations Density 0.224%

    No Known Activations