© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    references to the purpose or application of a process or action

    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
    interopRequire
    -0.79
     NSCoder
    -0.79
    ^(@)
    -0.75
     ComVisible
    -0.74
    +:+
    -0.69
    setViewportView
    -0.68
    SEGUIR
    -0.68
    amentals
    -0.66
     Reſ
    -0.66
     ThemeData
    -0.66
    POSITIVE LOGITS
     disponibilités
    0.58
    Попис
    0.54
    けている
    0.45
     nou
    0.44
     assoluto
    0.44
    relaxed
    0.42
     spirituale
    0.42
    x
    0.41
     spese
    0.41
     peines
    0.40
    Activations Density 0.283%

    No Known Activations