© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    seemingly random letters and punctuation after numbers or finds wiccan related words

    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
     smtplib
    -0.63
     contextLoads
    -0.54
     neighbor
    -0.48
     AppColors
    -0.47
     MediaQuery
    -0.47
     millis
    -0.47
     sauter
    -0.47
     peindre
    -0.44
     Italijanski
    -0.44
     resultCode
    -0.43
    POSITIVE LOGITS
    BagConstraints
    0.46
     biologie
    0.46
     vá
    0.44
     Asie
    0.44
     Dí
    0.43
     mou
    0.43
    kyou
    0.43
     tradi
    0.43
     typ
    0.42
     disulfide
    0.42
    Activations Density 0.043%

    No Known Activations