© 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. 12-RES-MATRYOSHKA-DC
    7. 30469
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns within repetitive sequences of characters or digits

    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
    Not in Any Lists

    No Comments

    Negative Logits
    FormTagHelper
    -0.77
    verwijspagina
    -0.70
     <=",
    -0.66
    ScopeManager
    -0.65
     StringTokenizer
    -0.63
    存于互联网档案馆
    -0.62
    JspWriter
    -0.61
     Wicidata
    -0.59
     تكبرها
    -0.57
    waitKey
    -0.57
    POSITIVE LOGITS
    tibus
    0.57
    vertret
    0.56
     الدولى
    0.56
     Recipro
    0.55
    htub
    0.54
    sette
    0.54
    Jeografia
    0.52
    apunov
    0.50
    VIAF
    0.50
     thể
    0.49
    Activations Density 0.048%

    No Known Activations