© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16396
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "usual"

    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
    RegressionTest
    -0.97
    protoimpl
    -0.96
    DataAnnotations
    -0.86
    Datuak
    -0.85
    SequentialGroup
    -0.81
    boards
    -0.77
    rawDesc
    -0.75
    GEBURTSDATUM
    -0.75
    ViewImports
    -0.74
     orthogonal
    -0.74
    POSITIVE LOGITS
    raisemb
    0.59
    pezif
    0.58
     Varian
    0.57
    ✸
    0.57
     Loeb
    0.56
    usual
    0.55
    FORMAN
    0.55
     IES
    0.55
    autogui
    0.55
     Fais
    0.53
    Activations Density 0.007%

    No Known Activations