© 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. 1-RES-MATRYOSHKA-DC
    7. 370
    Prev
    Next
    INDEX
    Explanations

    the highest numerical value associated with a specific mathematical parameter

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    potranspiration
    -0.62
     ANNE
    -0.55
    CPtr
    -0.54
    fancybox
    -0.54
    eadilan
    -0.53
    oredCriteria
    -0.53
    cardia
    -0.52
    visiae
    -0.52
    TSCA
    -0.52
     autoradio
    -0.51
    POSITIVE LOGITS
    Delta
    3.42
     delta
    3.36
     Delta
    3.28
    delta
    3.19
    DELTA
    2.84
     DELTA
    2.73
     Δ
    2.55
    Δ
    2.53
     deltas
    2.20
    ∆
    2.14
    Activations Density 0.631%

    No Known Activations