© 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. 10260
    Prev
    Next
    INDEX
    Explanations

    references to levels of physical activity

    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
    s
    -0.88
    l
    -0.76
    n
    -0.70
    </b>
    -0.69
    u
    -0.68
     s
    -0.68
    ...
    -0.66
     ill
    -0.65
    ic
    -0.65
     mis
    -0.65
    POSITIVE LOGITS
     Monfieur
    1.27
     Majefty
    1.23
     myſelf
    1.22
     themſelves
    1.21
     Theſe
    1.17
     Shakspeare
    1.16
     pleaſure
    1.16
     ―――――
    1.09
     ſeveral
    1.08
     Houſe
    1.07
    Activations Density 0.006%

    No Known Activations