© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5586
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical significance in research analysis

    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
     PhpStorm
    -0.51
    RegressionTest
    -0.50
    hemd
    -0.48
     letz
    -0.46
     zufolge
    -0.45
    OMAS
    -0.44
    ്
    -0.44
    klady
    -0.44
     aleg
    -0.43
     passa
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.86
    تقاوى
    0.86
    fortawesome
    0.76
    __*/
    0.74
    rungsseite
    0.71
    GEBURTSDATUM
    0.70
    Obrázky
    0.67
    TagMode
    0.66
    gway
    0.66
     pinulongan
    0.66
    Activations Density 0.059%

    No Known Activations