© 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. 2-RES-MATRYOSHKA-DC
    7. 7306
    Prev
    Next
    INDEX
    Explanations

    the concept of flying, specifically related to flying as a pilot or the act of flight

    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
    VersionUID
    -0.52
    ,
    -0.47
    -
    -0.47
     quickly
    -0.44
     digital
    -0.43
    .
    -0.43
     a
    -0.43
     meg
    -0.43
     and
    -0.42
     all
    -0.42
    POSITIVE LOGITS
    Vidite
    0.93
    出版年
    0.90
     мәкал
    0.90
     дописавши
    0.89
     Anſ
    0.87
     Shakspeare
    0.87
     myſelf
    0.83
     Theſe
    0.81
    Portail
    0.81
     Portail
    0.81
    Activations Density 1.317%

    No Known Activations