© 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. 18735
    Prev
    Next
    INDEX
    Explanations

    terms and metrics related to true and false positive and negative rates in statistical tests

    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
    Negative Logits
    اص
    -0.43
     den
    -0.41
    Ends
    -0.41
    nvarchar
    -0.41
    Lietu
    -0.40
     Sorg
    -0.39
     gau
    -0.38
    Locke
    -0.37
     vital
    -0.36
     benefits
    -0.35
    POSITIVE LOGITS
     beginnetje
    0.87
    ftagPool
    0.82
     ब्रेकडाउन
    0.79
    IUrlHelper
    0.77
    Jeografia
    0.76
    adaptiveStyles
    0.75
     שוליים
    0.74
    \{\\
    0.74
     Hän
    0.73
    parsedMessage
    0.73
    Activations Density 0.007%

    No Known Activations