© 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. 2-RES-MATRYOSHKA-DC
    7. 4658
    Prev
    Next
    INDEX
    Explanations

    references to source code or programming-related content

    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
     usando
    -1.10
     utilizzando
    -1.09
    using
    -1.09
     Use
    -1.06
    use
    -1.05
     using
    -1.04
     Using
    -1.03
     utilizando
    -1.02
    Use
    -1.02
     use
    -1.00
    POSITIVE LOGITS
     used
    2.20
     Used
    2.09
    Used
    2.08
     USED
    1.88
    used
    1.86
    USED
    1.42
     usada
    1.29
     usados
    1.24
     usado
    1.20
     utilizada
    1.16
    Activations Density 0.329%

    No Known Activations