© 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. 6375
    Prev
    Next
    INDEX
    Explanations

    terms related to handling processes and procedures

    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
     McClure
    -0.69
     Tinggi
    -0.68
    ież
    -0.68
    Обу
    -0.67
     Platt
    -0.66
     voters
    -0.65
    archer
    -0.65
     inspección
    -0.65
     Putih
    -0.65
     surfers
    -0.64
    POSITIVE LOGITS
     handled
    1.55
     handles
    1.50
     Handles
    1.48
    handled
    1.45
     handling
    1.41
    handling
    1.41
     dealt
    1.40
     Handle
    1.37
    handles
    1.37
     handle
    1.31
    Activations Density 0.131%

    No Known Activations