© 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. 6494
    Prev
    Next
    INDEX
    Explanations

    references to specific people, organizations, or labeled entities

    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
    n
    -0.77
     onOptions
    -0.63
    ún
    -0.61
    nthe
    -0.59
    ثيق
    -0.59
    mathscr
    -0.56
    годня
    -0.56
    Beno
    -0.56
    INSEE
    -0.53
     OBSERV
    -0.51
    POSITIVE LOGITS
     Ne
    3.03
    Ne
    2.88
     ne
    2.81
    ne
    2.47
     NE
    2.33
    NE
    2.23
     Neo
    1.62
     neo
    1.52
     Neville
    1.49
    Neo
    1.48
    Activations Density 0.204%

    No Known Activations