© 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. 26032
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical evaluation methods, particularly in the context of measuring areas under curves in data analysis

    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
    лару
    -0.60
    ="@+
    -0.54
    clientWidth
    -0.51
    Ciri
    -0.50
     Characteristics
    -0.50
    чо
    -0.50
    Characteristics
    -0.49
     autorytatywna
    -0.49
    agin
    -0.49
     око
    -0.47
    POSITIVE LOGITS
     AUC
    0.97
    AUC
    0.96
    Geplaatst
    0.80
     consultato
    0.77
    sizeCache
    0.75
     AssemblyProduct
    0.68
     CWE
    0.64
    الإنجليزية
    0.63
    存于互联网档案馆
    0.63
    pexpr
    0.60
    Activations Density 0.003%

    No Known Activations