© 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. 15650
    Prev
    Next
    INDEX
    Explanations

    terms related to approximation and estimation in mathematical contexts

    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
    IsMutable
    -0.87
     незавершена
    -0.80
     فريبيس
    -0.77
    ManagedBean
    -0.76
    LayoutStyle
    -0.76
    PerformLayout
    -0.75
    yarnpkg
    -0.71
    nestjs
    -0.71
    Lid
    -0.68
     OnInit
    -0.66
    POSITIVE LOGITS
    ximation
    0.84
     Approximation
    0.84
     approximation
    0.82
     Braxton
    0.81
     approximations
    0.78
     Circa
    0.77
     approximated
    0.67
     okru
    0.67
     bescha
    0.67
    setPage
    0.66
    Activations Density 0.011%

    No Known Activations