© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1063
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Colman
    -0.52
    GRANTED
    -0.51
    jątk
    -0.50
     surla
    -0.48
    lüssel
    -0.48
     Observ
    -0.48
     Quin
    -0.47
     Labs
    -0.47
     balk
    -0.47
     ترک
    -0.47
    POSITIVE LOGITS
    usepackage
    1.27
     EconPapers
    0.86
     تضيفلها
    0.61
    ISupport
    0.60
     pacote
    0.56
     CURLOPT
    0.56
     pineapple
    0.55
    ={({
    0.55
     пакет
    0.55
    AndEndTag
    0.55
    Activations Density 0.008%

    No Known Activations