© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    references to notable personalities in design and fashion

    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
    GEBURTSDATUM
    -1.50
     typelib
    -1.14
    Personendaten
    -1.14
     дописавши
    -1.09
    parsedMessage
    -1.07
     ویکی‌پدی
    -1.05
    principalTable
    -1.05
    下载附件
    -1.05
    Parcelize
    -1.00
    تقاوى
    -0.99
    POSITIVE LOGITS
    t
    0.42
    ),
    0.42
    el
    0.42
    )
    0.41
    <i>
    0.40
    for
    0.40
    <em>
    0.39
    or
    0.39
    <u>
    0.39
    ی
    0.39
    Activations Density 4.045%

    No Known Activations