© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 20938
    Prev
    Next
    INDEX
    Explanations

    terms related to specific physical processes or phenomena

    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
    клопе
    -0.67
    makeConstraints
    -0.61
     perten
    -0.49
     escen
    -0.47
    bitField
    -0.46
     createSlice
    -0.46
     one
    -0.43
    chod
    -0.43
     пои
    -0.42
     πραγ
    -0.42
    POSITIVE LOGITS
    PhysRev
    0.85
    GraphicsUnit
    0.79
    SqlClient
    0.71
     AppColors
    0.70
    StoryboardSegue
    0.69
    initState
    0.68
    viewDidLoad
    0.67
     通販
    0.65
     Cæsar
    0.65
     Alph
    0.65
    Activations Density 0.148%

    No Known Activations