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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16390
    Prev
    Next
    INDEX
    Explanations

    the frequent mention of the word "new."

    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
    نسية
    -0.48
     Nuevas
    -0.48
     fresh
    -0.47
    encre
    -0.44
    New
    -0.43
     further
    -0.43
     novas
    -0.43
     frische
    -0.42
     New
    -0.42
     Tân
    -0.42
    POSITIVE LOGITS
     "..\..\
    0.85
     Hivatalos
    0.81
     Thier
    0.78
     
    0.77
     المعيارى
    0.77
    intios
    0.75
     "..\..\..\
    0.75
    }/${
    0.73
    évaluateur
    0.72
     Burrell
    0.72
    Activations Density 0.027%

    No Known Activations