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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8524
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or optimization concepts, particularly in the context of Lagrange multipliers and decision-making processes in problems

    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
    uxxxx
    -0.85
     OFDb
    -0.83
    Hentet
    -0.82
    UrlResolution
    -0.79
     surla
    -0.75
    Sucesor
    -0.72
    PreInfinity
    -0.72
    SourceChecksum
    -0.72
    RegressionTest
    -0.71
     wireType
    -0.71
    POSITIVE LOGITS
     Martens
    0.47
    endre
    0.47
     workout
    0.47
    Linq
    0.46
     documentary
    0.46
     Liberty
    0.45
     Winaray
    0.44
    Constraint
    0.44
    encing
    0.42
     sztu
    0.42
    Activations Density 0.036%

    No Known Activations