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. 23663
    Prev
    Next
    INDEX
    Explanations

    terms associated with mathematical or physical equations

    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
    :✨
    -0.67
     getRequest
    -0.63
    <?
    
    -0.62
    )");
    
    -0.59
     getX
    -0.59
    **
    
    -0.57
     _)
    -0.56
    }}}}
    -0.56
    ebvre
    -0.56
     verk
    -0.55
    POSITIVE LOGITS
    IntoConstraints
    0.70
    modelBuilder
    0.67
    المناصب
    0.63
     SwiftUI
    0.61
    MessageDigest
    0.61
    存于互联网档案馆
    0.58
    DebuggerStep
    0.57
    évaluateur
    0.57
     '\\;'
    0.57
     LUMP
    0.57
    Activations Density 0.013%

    No Known Activations