© 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. 936
    Prev
    Next
    INDEX
    Explanations

    the maximum values of relevant geometric or numerical parameters

    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
     amet
    -0.59
     tiểu
    -0.51
    ValueStyle
    -0.50
    pis
    -0.49
    MENAFN
    -0.49
    htë
    -0.47
     minu
    -0.47
    UrlResolution
    -0.46
    isDirectory
    -0.45
    ọi
    -0.45
    POSITIVE LOGITS
     max
    3.94
    max
    3.89
    Max
    3.73
     Max
    3.72
    MAX
    3.44
     MAX
    3.39
     maximum
    3.13
     Maximum
    2.89
    maximum
    2.83
    Maximum
    2.75
    Activations Density 0.131%

    No Known Activations