Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 62
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and management 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
    hyrchwyd
    -0.60
    )),
    
    -0.59
    '):
    
    -0.58
    ]),
    
    -0.57
     ').
    -0.57
    )];
    
    -0.57
     '
    -0.56
     quite
    -0.55
    ])),
    -0.54
     so
    -0.54
    POSITIVE LOGITS
     etc
    1.17
     usw
    0.96
    etc
    0.95
     Etc
    0.89
     חיצוניים
    0.83
     그리고
    0.80
     kasarigan
    0.78
     CURIAM
    0.77
     كومونز
    0.73
     itſelf
    0.71
    Activations Density 4.587%

    No Known Activations