© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13029
    Prev
    Next
    INDEX
    Explanations

    references to technical terms related to spectrum data analysis and optical measurement techniques

    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
     interfer
    -0.65
     inception
    -0.53
    ADMINISTR
    -0.53
    multline
    -0.50
    Cody
    -0.49
    ciales
    -0.49
     démocratie
    -0.49
    attaque
    -0.48
    ANTLR
    -0.48
     túi
    -0.47
    POSITIVE LOGITS
     recti
    1.56
     rectification
    1.48
    rometers
    1.42
     rectified
    1.32
    rometer
    1.30
     rectifier
    1.27
     rectify
    1.21
     Neumann
    1.02
    webElementXpaths
    0.88
     RECT
    0.72
    Activations Density 0.002%

    No Known Activations