Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 30223
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to credit and discrimination laws

    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
    IUrlHelper
    -0.79
    drawSprites
    -0.63
    انتهای
    -0.57
    /−
    -0.55
     onOptions
    -0.51
    Vidite
    -0.50
     rood
    -0.50
     Ohne
    -0.50
    ->___
    -0.49
     تانيه
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.68
    NewUrlParser
    0.60
    complexType
    0.57
    bindParam
    0.57
    Искәрмәләр
    0.54
    HttpException
    0.54
    typeparam
    0.52
    NameValuePair
    0.52
     betweenstory
    0.52
    Coordonnées
    0.51
    Activations Density 0.016%

    No Known Activations