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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24582
    Prev
    Next
    INDEX
    Explanations

    phrases related to details in legal or formal documents

    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
    TestTools
    -0.41
    bigcap
    -0.41
    ness
    -0.40
     list
    -0.40
    subplots
    -0.40
    ducers
    -0.39
     Phenomena
    -0.39
    IONE
    -0.38
    юр
    -0.38
    vantaged
    -0.38
    POSITIVE LOGITS
    原始内容存档于
    0.66
    TemporalType
    0.66
    Personendaten
    0.64
     còn
    0.62
     <>",
    0.62
    ItemBackground
    0.62
     edelstahl
    0.61
    FunctionFlags
    0.60
    FailureListener
    0.60
    ItemLayout
    0.60
    Activations Density 0.220%

    No Known Activations