© 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. 16588
    Prev
    Next
    INDEX
    Explanations

    phrases referencing results and findings from studies or experiments

    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
     समीक्षक
    -0.72
     CreateTagHelper
    -0.70
    addContainerGap
    -0.70
    HasAnnotation
    -0.69
    참고
    -0.69
    ruptcy
    -0.68
     noqa
    -0.66
     rospy
    -0.66
    存于互联网档案馆
    -0.65
    tvguidetime
    -0.65
    POSITIVE LOGITS
     čet
    0.62
     fatica
    0.61
    onsumsi
    0.60
     rayures
    0.57
     experiments
    0.57
     twain
    0.56
     quæ
    0.54
     urma
    0.54
    accumulative
    0.52
     esfuerzo
    0.52
    Activations Density 0.046%

    No Known Activations