© 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. 32522
    Prev
    Next
    INDEX
    Explanations

    numerical values within the text

    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
    iastes
    -0.62
     voulais
    -0.57
     الحره
    -0.55
    UnsafeEnabled
    -0.55
     représ
    -0.54
     utama
    -0.54
     Hildebrand
    -0.53
    énario
    -0.51
     来自
    -0.51
     răsp
    -0.51
    POSITIVE LOGITS
    fjspx
    0.71
    CompilerServices
    0.69
    EXTERN
    0.68
     Irr
    0.66
    scriptcase
    0.66
    FontOfSize
    0.66
     }{@
    0.65
    AfterClass
    0.63
    chartInstance
    0.63
    IZ
    0.62
    Activations Density 0.026%

    No Known Activations