© 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. 1291
    Prev
    Next
    INDEX
    Explanations

    a specific pattern of characters regardless of context

    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
    S
    -0.69
     same
    -0.62
    same
    -0.57
    R
    -0.54
     doulou
    -0.54
     numériques
    -0.54
    I
    -0.54
    ool
    -0.54
    Same
    -0.53
    o
    -0.50
    POSITIVE LOGITS
    Portale
    0.84
    writeFieldEnd
    0.80
    SharedCtor
    0.77
    DoubleQuotes
    0.76
     AspNetCore
    0.75
     ExecuteAsync
    0.75
     <<<<<<<<<<<<<<
    0.74
    GEBURTSDATUM
    0.73
     saites
    0.73
     الحره
    0.72
    Activations Density 0.659%

    No Known Activations