© 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. 15237
    Prev
    Next
    INDEX
    Explanations

    specific dietary patterns and their classifications

    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
    istisches
    -0.60
     rather
    -0.49
    .
    -0.47
     and
    -0.46
     but
    -0.45
     Bet
    -0.44
     mis
    -0.44
    /
    -0.43
     så
    -0.42
     side
    -0.42
    POSITIVE LOGITS
     reaſon
    0.94
     themſelves
    0.92
    ſelf
    0.91
     Efq
    0.91
     ſtand
    0.91
     Theſe
    0.90
     itſelf
    0.89
     AssemblyCompany
    0.88
     myſelf
    0.87
     whoſe
    0.87
    Activations Density 0.081%

    No Known Activations