© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments regarding trial procedures and ineffective assistance of counsel

    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
    SizeF
    -0.59
    ilever
    -0.49
    urity
    -0.48
    textAlignment
    -0.47
    xique
    -0.46
    MSK
    -0.46
    cibo
    -0.45
    NIP
    -0.43
     McIntosh
    -0.43
    SAP
    -0.43
    POSITIVE LOGITS
     gdyby
    1.02
    would
    1.01
     would
    0.98
     hätte
    0.94
     wäre
    0.92
    Would
    0.85
     hubiera
    0.85
     WOULD
    0.85
     olisi
    0.83
     Would
    0.82
    Activations Density 0.884%

    No Known Activations