© 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. 17440
    Prev
    Next
    INDEX
    Explanations

    phrases related to messages being forwarded

    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
    MemoryWarning
    -0.87
    MLLoader
    -0.79
    umumkan
    -0.69
    TestingModule
    -0.66
    بوابة
    -0.64
     '\\;'
    -0.63
    vaig
    -0.63
     éché
    -0.62
     كومونز
    -0.61
     mAdapter
    -0.61
    POSITIVE LOGITS
    warded
    0.58
    Original
    0.58
    LayoutStyle
    0.57
    RectangleBorder
    0.54
     calcu
    0.51
     Original
    0.50
    gna
    0.49
     original
    0.48
    anguages
    0.46
    Ữ
    0.46
    Activations Density 0.001%

    No Known Activations