© 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. 980
    Prev
    Next
    INDEX
    Explanations

    references to specific statistical parameters related to the symbol "tau"

    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
    __':
    -0.64
     ODS
    -0.64
    felizmente
    -0.63
     (°
    -0.61
     Firestone
    -0.60
     Alchemy
    -0.57
     Ahmed
    -0.57
    Ahmed
    -0.57
     Benton
    -0.56
    AMG
    -0.56
    POSITIVE LOGITS
    tau
    3.64
     tau
    2.61
    Tau
    2.53
     Tau
    2.48
    τ
    1.69
    ta
    1.61
     Ta
    1.52
    TA
    1.51
    taus
    1.51
     ta
    1.48
    Activations Density 0.373%

    No Known Activations