© 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. 625
    Prev
    Next
    INDEX
    Explanations

    patterns involving a specific parameter called theta

    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
     plait
    -0.67
     McFadden
    -0.65
     bacon
    -0.63
    theless
    -0.61
    Mandy
    -0.61
    Cyfeiriadau
    -0.59
    Tracy
    -0.59
    Bacon
    -0.58
     Plugins
    -0.58
     Tracy
    -0.57
    POSITIVE LOGITS
    theta
    3.56
     theta
    2.84
    θ
    2.41
     θ
    2.34
    Theta
    2.03
     Theta
    1.88
    𝜃
    1.70
    Θ
    1.45
    vartheta
    1.30
     Θ
    1.20
    Activations Density 0.027%

    No Known Activations