© 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. 24-RES-MATRYOSHKA-DC
    7. 1356
    Prev
    Next
    INDEX
    Explanations

    sentences expressing conditions, alternatives, or hypothetical scenarios

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     напря
    -0.45
     StatefulWidget
    -0.43
     AssemblyTitle
    -0.43
    LookAnd
    -0.42
    êques
    -0.42
     prolongation
    -0.42
    NNY
    -0.42
    Signup
    -0.41
     entrer
    -0.41
     Slow
    -0.41
    POSITIVE LOGITS
     removal
    2.27
     removed
    2.14
     remove
    2.11
     removing
    2.11
     Removal
    2.03
     Removing
    1.95
     removes
    1.91
     Remove
    1.88
    Removing
    1.85
     REMOV
    1.84
    Activations Density 2.943%

    No Known Activations