© 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. 337
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, formulas, or indices related to equations and numerical methods

    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
    enterOuterAlt
    -0.75
    MessageOf
    -0.73
     strto
    -0.70
    Искәрмәләр
    -0.60
    tagHelperRunner
    -0.59
     comunicado
    -0.57
    Derbyniad
    -0.56
     rospy
    -0.55
    󠁣
    -0.55
     Lovato
    -0.53
    POSITIVE LOGITS
     index
    4.81
     Index
    4.44
    index
    4.25
    Index
    4.16
     INDEX
    3.92
    INDEX
    3.75
     indexes
    3.56
     indices
    3.50
     Indexes
    3.19
     Indices
    3.17
    Activations Density 0.250%

    No Known Activations