© 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. 3-RES-MATRYOSHKA-DC
    7. 1768
    Prev
    Next
    INDEX
    Explanations

    references to characters, objects, and attacks with the word "Meteor" in a show called "Ryuteioh"

    oai_token-act-pair · gemini-2.0-flash
    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
    ExtendWith
    -0.88
    rawDesc
    -0.84
     Rued
    -0.82
    CWE
    -0.81
     Bakar
    -0.79
    AnchorTagHelper
    -0.76
    qtt
    -0.75
     Rha
    -0.74
    __*/
    -0.74
     Gart
    -0.73
    POSITIVE LOGITS
     Scro
    0.87
     Crot
    0.87
    HCR
    0.82
     Kitty
    0.77
     Apache
    0.73
     Kohlen
    0.71
     LOD
    0.71
     Oph
    0.70
     Boek
    0.70
     kokona
    0.69
    Activations Density 4.642%

    No Known Activations