© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    terms related to the conception, design, and analysis of experiments or research studies

    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
    </caption>
    -0.68
    AndEndTag
    -0.63
     onlyOwner
    -0.60
    rdom
    -0.59
    Skocz
    -0.59
    IndentedString
    -0.59
    ்கு
    -0.58
    ConstraintLayout
    -0.57
    interopRequire
    -0.57
     arşivlendi
    -0.57
    POSITIVE LOGITS
    RTGC
    0.72
     فريبيس
    0.71
    ReusableCell
    0.71
     <>",
    0.66
    RenderAtEndOf
    0.56
    principalColumn
    0.54
     scom
    0.53
     actifs
    0.52
    كويكب
    0.52
     Exacts
    0.51
    Activations Density 0.022%

    No Known Activations