© 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. 18-RES-MATRYOSHKA-DC
    7. 1349
    Prev
    Next
    INDEX
    Explanations

    words related to the presentation and manipulation of ideas

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    こうした
    -0.68
    ؤلاء
    -0.61
    これらの
    -0.61
    このような
    -0.59
    исленность
    -0.59
     these
    -0.56
    Distribuzione
    -0.55
    こういった
    -0.55
    these
    -0.53
    러한
    -0.53
    POSITIVE LOGITS
     it
    2.53
    它
    1.90
     оно
    1.81
     nó
    1.63
     ervan
    1.51
    它是
    1.48
     Оно
    1.45
     esso
    1.43
     它
    1.42
    It
    1.41
    Activations Density 2.828%

    No Known Activations