© 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. 18-RES-MATRYOSHKA-DC
    7. 73
    Prev
    Next
    INDEX
    Explanations

    descriptions of events and observations, often including locations apartment, window, door, stairs, and other people witness, lady, husband

    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.18.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.18.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
     vermogen
    -0.63
     berücksichtigt
    -0.62
     inclusión
    -0.62
     actualmente
    -0.61
     Historically
    -0.60
     jährlich
    -0.60
    Historically
    -0.60
     criterio
    -0.60
    ennials
    -0.59
     atualmente
    -0.59
    POSITIVE LOGITS
     downstairs
    0.81
     suddenly
    0.78
     upstairs
    0.77
     smelling
    0.75
     wearing
    0.74
     frantically
    0.73
     motionless
    0.72
     impromptu
    0.72
     nearby
    0.70
     makeshift
    0.70
    Activations Density 11.177%

    No Known Activations