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. 19663
    Prev
    Next
    INDEX
    Explanations

    mentions of library-related terms or functions

    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
     Libraries
    -1.05
     libraries
    -1.04
    ']))
    
    -1.00
    ſelf
    -0.99
    ']")
    -0.95
    )");
    
    -0.95
     LIBRARIES
    -0.92
    }")
    
    -0.92
     dieß
    -0.92
    "]);
    
    -0.90
    POSITIVE LOGITS
    toEqual
    0.73
    IContainer
    0.70
    tod
    0.63
    Ned
    0.63
    extAlignment
    0.61
    ubmit
    0.61
     ANO
    0.61
    Shaun
    0.59
    term
    0.59
    loch
    0.58
    Activations Density 0.004%

    No Known Activations