© 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. 128
    Prev
    Next
    INDEX
    Explanations

    parts of code such as data types, classes, or interfaces and related keywords

    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
     /\.(
    -0.62
    Clik
    -0.60
     eventName
    -0.57
     eventId
    -0.56
    ----</
    -0.55
     fileSize
    -0.54
     photolibrary
    -0.54
     〈
    -0.54
     roomId
    -0.54
     `"
    -0.53
    POSITIVE LOGITS
    BeginContext
    0.76
     result
    0.76
    Personendaten
    0.75
     temp
    0.68
     old
    0.66
     s
    0.63
     i
    0.63
     v
    0.62
     p
    0.62
     tmp
    0.61
    Activations Density 1.361%

    No Known Activations