© 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. 22-RES-MATRYOSHKA-DC
    7. 1937
    Prev
    Next
    INDEX
    Explanations

    words associated with switches and levers

    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.22.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.22.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
    ]--;
    -0.59
     thickly
    -0.56
    })}\
    -0.56
    EndContext
    -0.56
     CURIAM
    -0.55
     thinned
    -0.55
    Autoritní
    -0.53
    BeginInit
    -0.52
    ItemGroup
    -0.52
    Rptr
    -0.50
    POSITIVE LOGITS
     spring
    0.92
    spring
    0.78
     Spring
    0.77
    Spring
    0.76
     movement
    0.76
     springs
    0.75
     lock
    0.73
     levers
    0.71
     push
    0.71
     engagement
    0.71
    Activations Density 0.896%

    No Known Activations