© 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. 2-RES-MATRYOSHKA-DC
    7. 7022
    Prev
    Next
    INDEX
    Explanations

    references to request handling operations in code

    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
    R
    -1.09
     R
    -1.08
     Rar
    -0.78
    mR
    -0.77
     ddelweddau
    -0.66
    verwijspagina
    -0.65
     Rak
    -0.63
     propOrder
    -0.61
    Ｒ
    -0.60
    Rak
    -0.59
    POSITIVE LOGITS
    r
    1.17
     r
    0.90
    rC
    0.78
    rA
    0.78
    rB
    0.76
     AssemblyVersion
    0.69
    Xr
    0.68
    ValueStyle
    0.67
    原始内容存档于
    0.66
     Corso
    0.64
    Activations Density 0.096%

    No Known Activations