© 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. 16091
    Prev
    Next
    INDEX
    Explanations

    words or concepts that indicate significance or importance

    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
     للاسماء
    -1.01
     PopupWindow
    -0.89
    AdapterView
    -0.79
    thodon
    -0.78
     DriverManager
    -0.75
    preduce
    -0.75
     Entra
    -0.74
    Entra
    -0.69
    LEncoder
    -0.69
    endaftar
    -0.68
    POSITIVE LOGITS
    a
    0.92
    }]
    0.79
    kritik
    0.79
    CRITICAL
    0.77
     CRITICAL
    0.77
     Critical
    0.75
    endregion
    0.72
    Critical
    0.71
     Kalt
    0.70
     Kri
    0.68
    Activations Density 0.019%

    No Known Activations