© 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. 144
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or contexts, particularly those prefaced by "under."

    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
    脚注の使い方
    -0.98
    بوابة
    -0.82
    RSpec
    -0.79
    Portale
    -0.79
    ✨:
    -0.77
     MainAxisSize
    -0.77
     HttpNotFound
    -0.75
     Pingback
    -0.73
    StoryboardSegue
    -0.72
    DataSetChanged
    -0.71
    POSITIVE LOGITS
    Under
    1.72
     Under
    1.70
     under
    1.64
    under
    1.60
     UNDER
    1.58
    UNDER
    1.58
    neath
    1.36
    Bajo
    1.33
     Underwood
    1.20
     bajo
    1.17
    Activations Density 0.806%

    No Known Activations