© 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. 1460
    Prev
    Next
    INDEX
    Explanations

    text related to chemistry and spectral analysis, especially chemical shifts and carbon positions

    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
    ticity
    -0.65
    riente
    -0.57
    gridx
    -0.57
    érons
    -0.56
    يكب
    -0.56
     pase
    -0.54
    rungsseite
    -0.54
     lenker
    -0.54
     Quote
    -0.54
    entgen
    -0.53
    POSITIVE LOGITS
     Himo
    0.68
    CDCl
    0.60
     שוליים
    0.50
     springfox
    0.50
    TagMode
    0.49
    DataAnnotations
    0.47
    masing
    0.46
    */),
    0.46
    getOriginal
    0.44
    ulemon
    0.44
    Activations Density 0.374%

    No Known Activations