© 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. 3131
    Prev
    Next
    INDEX
    Explanations

    references to structural or molecular alterations and changes

    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
    change
    -1.17
    Change
    -1.11
     Change
    -1.11
     change
    -1.03
     CHANGE
    -1.02
    CHANGE
    -0.93
    ContentAsync
    -0.79
     changer
    -0.75
     cambio
    -0.74
    yntaxException
    -0.72
    POSITIVE LOGITS
     changes
    1.52
    Changes
    1.41
     Changes
    1.37
     CHANGES
    1.15
    changes
    1.13
    CHANGES
    0.96
     alterations
    0.84
     Änderungen
    0.82
     updates
    0.82
     modifications
    0.79
    Activations Density 0.087%

    No Known Activations