© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12747
    Prev
    Next
    INDEX
    Explanations

    references to visual or scenic elements in a context, such as a backdrop or setting

    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
     חיצוניים
    -0.81
    apunov
    -0.75
     ModelAndView
    -0.62
    nocache
    -0.61
    vismo
    -0.59
    featureID
    -0.58
    Controllo
    -0.58
    SpringBootTest
    -0.58
    Diweddarwch
    -0.57
    gorithm
    -0.55
    POSITIVE LOGITS
     backdrop
    3.52
    backdrop
    2.67
    Backdrop
    1.84
     soundtrack
    0.68
     tapestry
    0.65
    drops
    0.65
     cenário
    0.62
     curtain
    0.62
     paisagem
    0.62
    ٰ
    0.61
    Activations Density 0.000%

    No Known Activations