© 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. 32181
    Prev
    Next
    INDEX
    Explanations

    specific legal terminology and concepts related to political campaign regulations

    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
    Next
    -0.47
    劣
    -0.45
    next
    -0.44
    quien
    -0.43
     Next
    -0.40
    y
    -0.39
    better
    -0.38
     femininas
    -0.37
     metais
    -0.37
     itong
    -0.36
    POSITIVE LOGITS
     дописавши
    1.00
    featureID
    0.92
    RectangleBorder
    0.78
    RenderAtEndOf
    0.77
    djangoproject
    0.75
    VIAF
    0.73
    ValueStyle
    0.73
    [::-
    0.72
     lenker
    0.71
    underland
    0.71
    Activations Density 0.030%

    No Known Activations