© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 653
    Prev
    Next
    INDEX
    Explanations

    technical terms, names, and abbreviations that include the letters "ac", "ci", "sc", or "uc"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
    ธ์
    -0.76
    modelBuilder
    -0.74
     DBNull
    -0.74
     getItemId
    -0.74
     nahilalakip
    -0.73
     kasarigan
    -0.71
    Hauptartikel
    -0.71
    abestanden
    -0.69
     Мексичка
    -0.69
    POSITIVE LOGITS
    ac
    0.75
     Kac
    0.71
    lec
    0.65
    ic
    0.64
     Rac
    0.63
    tac
    0.63
    poc
    0.63
    Buc
    0.63
    Coc
    0.61
     Toc
    0.61
    Activations Density 0.917%

    No Known Activations