© 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. 360
    Prev
    Next
    INDEX
    Explanations

    technical terms related to nanotechnology and materials science

    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
     itſelf
    -0.86
     Efq
    -0.85
     Chriftian
    -0.78
     Majefty
    -0.78
     reaſon
    -0.77
     fubject
    -0.75
     myſelf
    -0.75
     purpoſe
    -0.73
     ſhe
    -0.72
     unſ
    -0.72
    POSITIVE LOGITS
    ånd
    0.52
    Unmarshaller
    0.51
    ing
    0.50
    AnchorStyles
    0.49
    Externé
    0.48
     rê
    0.48
    åne
    0.48
    makeConstraints
    0.47
    цепт
    0.47
    wige
    0.47
    Activations Density 8.681%

    No Known Activations