© 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. 0-RES-MATRYOSHKA-DC
    7. 11784
    Prev
    Next
    INDEX
    Explanations

    references to the process of generating or establishing new instances or representations, particularly emphasizing the concept of creation

    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
    MigrationBuilder
    -0.66
    évaluateur
    -0.65
     surla
    -0.62
     Formations
    -0.59
    Personensuche
    -0.56
    hObject
    -0.54
    Lähteet
    -0.53
     formations
    -0.53
    encodeWith
    -0.50
    StoreMessageInfo
    -0.50
    POSITIVE LOGITS
     creation
    1.93
    creation
    1.83
     Creation
    1.73
    Creation
    1.68
     creations
    1.05
     création
    1.04
     creación
    1.00
     creazione
    0.84
     forming
    0.79
     criação
    0.77
    Activations Density 0.002%

    No Known Activations