© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5054
    Prev
    Next
    INDEX
    Explanations

    content related to Hamiltonian mechanics and energy levels in quantum systems

    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
     count
    -0.55
    ::$_
    -0.52
    GEBURTSDATUM
    -0.52
    rungsseite
    -0.50
     الرياضيه
    -0.50
     ModelExpression
    -0.49
    mapreduce
    -0.47
    enterOuterAlt
    -0.46
    atouille
    -0.46
    vignon
    -0.45
    POSITIVE LOGITS
    MemoryWarning
    0.68
     Pensions
    0.65
     groupName
    0.63
     <>",
    0.63
    RegressionTest
    0.61
     bounties
    0.61
     pensions
    0.60
     Salas
    0.59
     salaries
    0.56
    JsonValue
    0.55
    Activations Density 0.239%

    No Known Activations