© 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. 0-RES-MATRYOSHKA-DC
    7. 11233
    Prev
    Next
    INDEX
    Explanations

    references to the quasistatic approximation or concept

    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
     rip
    -0.60
    ynthetic
    -0.59
    Geplaatst
    -0.54
     Anand
    -0.52
     الحره
    -0.51
    principalTable
    -0.51
     heal
    -0.51
     coherence
    -0.51
    cosm
    -0.51
    groom
    -0.50
    POSITIVE LOGITS
     quas
    1.16
     numbering
    1.03
     numbered
    1.00
    odes
    0.89
    AutoScaleMode
    0.81
     misplaced
    0.70
    webElementXpaths
    0.65
    ValueGeneration
    0.64
     елның
    0.62
    حياتها
    0.60
    Activations Density 0.007%

    No Known Activations