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. 10453
    Prev
    Next
    INDEX
    Explanations

    mathematical operations or equations involving derivatives

    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
     ISNI
    -0.89
     AssemblyCulture
    -0.79
     שוליים
    -0.76
     myſelf
    -0.76
     nahilalakip
    -0.72
     hObject
    -0.71
     estimés
    -0.71
    __["
    -0.70
     himſelf
    -0.70
    __':
    
    -0.70
    POSITIVE LOGITS
    &+
    0.69
    PositiveButton
    0.62
    odend
    0.56
    }+(
    0.51
    اخ
    0.50
     (+)
    0.50
    [+
    0.50
     +
    0.50
     And
    0.49
     plus
    0.48
    Activations Density 0.125%

    No Known Activations