© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    references to the process of using or employing specific analytical techniques or tools

    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
     used
    -1.06
    Used
    -1.04
    used
    -1.02
     Used
    -0.98
     use
    -0.96
    use
    -0.87
     USED
    -0.86
     käyttö
    -0.85
    Use
    -0.85
     Use
    -0.84
    POSITIVE LOGITS
     using
    1.63
     Using
    1.39
     USING
    1.35
     utilizando
    1.31
    using
    1.30
    Using
    1.28
     utilizzando
    1.22
     usando
    1.16
     menggunakan
    1.09
     utilisant
    1.04
    Activations Density 0.110%

    No Known Activations