© 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. 18504
    Prev
    Next
    INDEX
    Explanations

    phrases related to the adequacy of evidence in a legal context

    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
    Hozzáférés
    -0.88
     HasFactory
    -0.86
     createState
    -0.81
    SequentialGroup
    -0.79
    WebServlet
    -0.77
    principalTable
    -0.76
    okovic
    -0.75
    GenerationType
    -0.73
    __':
    -0.71
    اریخ
    -0.71
    POSITIVE LOGITS
     quotas
    0.43
     особо
    0.43
    lighed
    0.42
    عداد
    0.41
     representation
    0.41
     heti
    0.41
    komme
    0.41
     targets
    0.40
     comples
    0.40
    宾
    0.39
    Activations Density 0.016%

    No Known Activations