© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4537
    Prev
    Next
    INDEX
    Explanations

    references to the Earth's rotation or rotation of celestial bodies

    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
     spin
    -0.97
    spin
    -0.88
    Spin
    -0.84
    complexContent
    -0.84
     Spin
    -0.81
    SPIN
    -0.62
    Bronnen
    -0.60
    wyl
    -0.59
     chấm
    -0.58
     SPIN
    -0.56
    POSITIVE LOGITS
     rotation
    2.72
     rotate
    2.48
     rotations
    2.42
     Rotation
    2.41
     rotated
    2.28
     rotates
    2.20
    rotation
    2.16
     Rotate
    2.13
    Rotation
    2.05
     rotating
    1.84
    Activations Density 0.031%

    No Known Activations