© 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. 22-RES-MATRYOSHKA-DC
    7. 3017
    Prev
    Next
    INDEX
    Explanations

    very common characters such as digits and punctuation, especially when near other digits

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     незавершена
    -0.71
    oredCriteria
    -0.57
    ]--;
    -0.56
     cherchés
    -0.55
     Maat
    -0.54
    RTSC
    -0.53
     fee
    -0.53
     Whigs
    -0.52
    ]^{-
    -0.51
    WireFormatLite
    -0.50
    POSITIVE LOGITS
     AssemblyProduct
    0.48
    toggler
    0.46
     />);
    0.46
     reizen
    0.44
     mostrou
    0.44
     {}));
    0.44
     saites
    0.43
     />}
    0.43
     professionnels
    0.43
     Leone
    0.43
    Activations Density 0.027%

    No Known Activations