© 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. 114
    Prev
    Next
    INDEX
    Explanations

    descriptive imagery related to physical appearance and facial features

    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
     soorten
    -0.70
     miei
    -0.61
     belangrij
    -0.60
    getValueAt
    -0.60
     gekomen
    -0.60
     religione
    -0.59
     genomen
    -0.58
     jasa
    -0.57
    simov
    -0.57
     lesiones
    -0.57
    POSITIVE LOGITS
     houſe
    1.07
     faſt
    1.07
     ―――――
    1.00
     ſtre
    0.92
     ſta
    0.91
     Houſe
    0.87
     ſtand
    0.86
    neſs
    0.84
     purpoſe
    0.83
     ſtate
    0.82
    Activations Density 22.591%

    No Known Activations