© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10825
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and affiliations

    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
    Autoritní
    -0.72
    ężczy
    -0.61
     виправивши
    -0.61
     ProtoMessage
    -0.60
     ExecuteAsync
    -0.60
     resourceCulture
    -0.58
    GeneratedCode
    -0.56
    "]();
    -0.56
    oa̍t
    -0.56
     AssemblyTitle
    -0.55
    POSITIVE LOGITS
     TextInputType
    0.59
     оригіналу
    0.54
     requestCode
    0.52
    rethe
    0.50
     onOptions
    0.50
    lhes
    0.48
    |')
    0.47
    slidesToShow
    0.47
     hâte
    0.47
    isis
    0.46
    Activations Density 5.573%

    No Known Activations