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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19560
    Prev
    Next
    INDEX
    Explanations

    quantitative or numerical information

    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
     فريبيس
    -0.82
     beginnetje
    -0.57
    hyrchwyd
    -0.57
    basicConfig
    -0.55
     للمعارف
    -0.54
    पया
    -0.54
    Datuak
    -0.54
    AnchorTagHelper
    -0.52
    الدراسه
    -0.50
     onCreateView
    -0.50
    POSITIVE LOGITS
     siquiera
    0.56
    Microkernel
    0.56
     esclavos
    0.53
    ="@
    0.51
     setuptools
    0.51
     feroit
    0.50
     Fairness
    0.50
     obé
    0.49
     auroit
    0.49
    ="#
    0.48
    Activations Density 0.088%

    No Known Activations