© 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. 6303
    Prev
    Next
    INDEX
    Explanations

    references to axes or directions in a three-dimensional coordinate system

    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
    uParam
    -0.72
    ex
    -0.60
     INTERESAR
    -0.58
     uParam
    -0.57
    :✨
    -0.54
     Armen
    -0.53
     oprot
    -0.53
    kkue
    -0.52
    EOUT
    -0.49
    omer
    -0.48
    POSITIVE LOGITS
     axis
    3.56
    axis
    3.16
     Axis
    3.05
    Axis
    2.88
     AXIS
    2.63
    AXIS
    2.56
     axes
    2.50
     Axes
    1.87
    轴
    1.85
    軸
    1.71
    Activations Density 0.008%

    No Known Activations