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. 25690
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to mechanical design and spatial configuration

    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
    ViewFeatures
    -0.61
     imageNamed
    -0.60
    WriteBarrier
    -0.60
     AspNetCore
    -0.60
     الرياضيه
    -0.56
     <=",
    -0.56
     initWithFrame
    -0.54
    المكان
    -0.53
     مشين
    -0.52
    irit
    -0.50
    POSITIVE LOGITS
     الدولى
    0.67
    MessageTagHelper
    0.64
     typelib
    0.62
    bootstrapcdn
    0.58
     purpoſe
    0.53
    //
    0.52
     surroundings
    0.51
    sipasi
    0.51
    reuung
    0.50
     Bekasi
    0.50
    Activations Density 0.174%

    No Known Activations