© 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. 759
    Prev
    Next
    INDEX
    Explanations

    references to mathematical constants, parameters, or equations

    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
     therefore
    -0.93
     however
    -0.90
     thus
    -0.81
     hence
    -0.74
     meanwhile
    -0.71
     also
    -0.66
    An
    -0.64
     now
    -0.63
    however
    -0.61
    therefore
    -0.60
    POSITIVE LOGITS
     Also
    1.30
     Lastly
    1.22
     Then
    1.21
     Anyway
    1.20
     Usually
    1.19
     Basically
    1.19
     Finally
    1.18
     Additionally
    1.18
     Actually
    1.17
     Anyways
    1.17
    Activations Density 1.472%

    No Known Activations