© 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. 8381
    Prev
    Next
    INDEX
    Explanations

    the presence of high-activation words that convey importance or significance in a context

    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
    zzar
    -0.55
    bootstrapcdn
    -0.51
     never
    -0.46
     Sharma
    -0.46
     Waray
    -0.46
    popd
    -0.46
    lectricité
    -0.45
    urllib
    -0.45
    neros
    -0.44
    ָׁ
    -0.44
    POSITIVE LOGITS
    tvguidetime
    1.20
     تضيفلها
    0.87
    ſelves
    0.85
    Datuak
    0.85
     Efq
    0.80
     Majefty
    0.79
     againſt
    0.78
     myſelf
    0.77
     houſe
    0.75
     itſelf
    0.73
    Activations Density 0.035%

    No Known Activations