Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16875
    Prev
    Next
    INDEX
    Explanations

    terminology related to acceleration and its various forms in physical or mechanical contexts

    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
    Vidite
    -0.94
     Winaray
    -0.80
    AdapterView
    -0.76
    idung
    -0.75
    bootstrapcdn
    -0.74
     logarith
    -0.73
    VIAF
    -0.72
     للاسماء
    -0.70
     AWG
    -0.70
    oglobulin
    -0.70
    POSITIVE LOGITS
     acceleration
    1.14
     Acceleration
    1.05
     acceler
    1.00
    acceler
    0.96
     accelerometer
    0.95
    Acceleration
    0.91
    ELER
    0.87
    acceleration
    0.86
     aceler
    0.83
     accelerates
    0.81
    Activations Density 0.010%

    No Known Activations