© 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. 9341
    Prev
    Next
    INDEX
    Explanations

    numerical representations and data points

    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
    IContainer
    -0.59
     valueOf
    -0.52
    uition
    -0.52
    AnimationsModule
    -0.50
    PerformLayout
    -0.50
     espagnole
    -0.49
    prnewswire
    -0.48
    companyname
    -0.48
    TProtocol
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     المعيارى
    0.56
     ouver
    0.53
     Pristupljeno
    0.52
     digitais
    0.52
    gın
    0.52
    }:${
    0.52
     تانيه
    0.51
     lèvres
    0.51
     الاطلاع
    0.50
    CloseOperation
    0.50
    Activations Density 0.001%

    No Known Activations