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. 32042
    Prev
    Next
    INDEX
    Explanations

    references to medical device types and 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
    +#+#
    -0.65
     AssemblyCulture
    -0.62
     Normdatei
    -0.54
    didSet
    -0.54
    ChildScrollView
    -0.53
    Personendaten
    -0.52
    DoubleQuotes
    -0.50
     diſt
    -0.49
    InsertCommand
    -0.48
    følgelig
    -0.48
    POSITIVE LOGITS
    loroethene
    0.64
    esgue
    0.61
     autorytatywna
    0.58
    GroupLayout
    0.56
    tagHelperRunner
    0.56
    queryInterface
    0.56
    oneofs
    0.54
    허
    0.51
    uchung
    0.51
    rscheinlichkeit
    0.51
    Activations Density 0.011%

    No Known Activations