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. 25404
    Prev
    Next
    INDEX
    Explanations

    references to specific websites or online platforms, particularly involving combinators

    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
    queryInterface
    -0.65
    Przypisy
    -0.64
     المعيارى
    -0.63
    licazione
    -0.61
    InjectAttribute
    -0.59
    TEMPO
    -0.56
    RTRS
    -0.55
    PageFactory
    -0.55
    DialogTitle
    -0.54
    cipitation
    -0.54
    POSITIVE LOGITS
    combin
    1.94
     Combin
    1.15
     combin
    1.12
    Combin
    1.01
     COMBIN
    0.83
     HN
    0.82
     Combine
    0.75
     combinatorial
    0.73
    Combine
    0.69
     combine
    0.69
    Activations Density 0.001%

    No Known Activations