© 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. 16294
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific notation related to programming and data structures

    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
     تضيفلها
    -1.02
    IVEREF
    -1.02
     ExecuteAsync
    -0.98
    хьтан
    -0.98
     kasarigan
    -0.95
    PyExc
    -0.88
    ValueStyle
    -0.85
    tangentMode
    -0.84
    uxxxx
    -0.82
     defaultstate
    -0.79
    POSITIVE LOGITS
    GCS
    0.47
    கு
    0.41
     bar
    0.40
     lo
    0.39
    atural
    0.37
     высоко
    0.37
     top
    0.36
    感を
    0.36
    ╭
    0.36
     short
    0.36
    Activations Density 0.002%

    No Known Activations