© 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. 3-RES-MATRYOSHKA-DC
    7. 2180
    Prev
    Next
    INDEX
    Explanations

    the forward slash character "/"

    oai_token-act-pair · gemini-2.0-flash
    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
    EndGlobalSection
    -0.84
    xaml
    -0.77
     propOrder
    -0.71
    InitVars
    -0.69
    FailureListener
    -0.68
     FetchType
    -0.67
    ClCompile
    -0.66
    AFX
    -0.64
    resave
    -0.64
    ertale
    -0.63
    POSITIVE LOGITS
    prnewswire
    0.65
    出版年
    0.56
    NonNull
    0.52
    igno
    0.50
     kli
    0.50
    ज्ञ
    0.47
     trov
    0.47
     못
    0.44
    tle
    0.44
    侃
    0.44
    Activations Density 1.327%

    No Known Activations