© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    the character "D" preceded by or part of the string "3D" or "dimensional"

    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
     estekak
    -0.74
    tagHelper
    -0.73
    MessageOf
    -0.68
    WireFormatLite
    -0.67
    GOTREF
    -0.66
     дописавши
    -0.65
     للاسماء
    -0.64
    Autoritní
    -0.63
     fieldNum
    -0.63
    AppMethodBeat
    -0.60
    POSITIVE LOGITS
    D
    0.61
    dimensional
    0.57
    DIC
    0.56
     Efficiency
    0.52
     "','
    0.50
     efficiency
    0.50
     Dimensional
    0.50
    ICI
    0.49
    F
    0.49
     consom
    0.48
    Activations Density 0.068%

    No Known Activations