© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 531
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical data and their stability

    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
     Janeiro
    -0.84
    ])):
    -0.82
     Inhabitants
    -0.81
     Purcell
    -0.77
    /*
    -0.76
    cznej
    -0.75
     UCB
    -0.75
     Healey
    -0.75
     useCallback
    -0.75
    Notae
    -0.75
    POSITIVE LOGITS
     Stur
    1.08
     ST
    1.02
     st
    0.93
     Stony
    0.93
     Sta
    0.91
     Stanis
    0.91
     STAN
    0.88
     St
    0.87
    St
    0.86
     Sten
    0.85
    Activations Density 1.423%

    No Known Activations