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. 9546
    Prev
    Next
    INDEX
    Explanations

    specific identifiers for hardware components or configurations

    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
    帖最后由
    -0.94
    ANDUM
    -0.86
     Wiktionnaire
    -0.79
     Jaffe
    -0.79
    Sortie
    -0.77
     Inga
    -0.75
    potranspiration
    -0.72
    matchCondition
    -0.71
    المشاركات
    -0.71
    LETIN
    -0.70
    POSITIVE LOGITS
    ece
    1.05
     Reece
    0.87
     gouver
    0.66
     ECE
    0.61
     nozze
    0.61
    vičius
    0.60
    CHE
    0.57
     BCM
    0.57
    rece
    0.56
    most
    0.55
    Activations Density 0.000%

    No Known Activations