© 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. 12-RES-MATRYOSHKA-DC
    7. 21271
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities with the name "Cas."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Pires
    -0.97
     Wikimedijinoj
    -0.84
    ámide
    -0.83
    enso
    -0.82
     Partagez
    -0.82
     Sardegna
    -0.79
     inhalation
    -0.79
     Biro
    -0.78
     Lungen
    -0.78
     rojos
    -0.76
    POSITIVE LOGITS
    Cas
    1.82
     Cas
    1.78
     cas
    1.51
    cas
    1.45
     CAS
    1.39
    CascadeType
    1.27
    CAS
    1.15
     Castillo
    1.12
     Cassel
    1.09
     Casio
    1.08
    Activations Density 0.008%

    No Known Activations