© 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. 3971
    Prev
    Next
    INDEX
    Explanations

    references to prior or earlier 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
     previously
    -1.59
     formerly
    -1.56
     recently
    -1.48
    recently
    -1.32
     heretofore
    -1.30
    previously
    -1.30
     Formerly
    -1.27
     Previously
    -1.20
    Previously
    -1.16
    formerly
    -1.16
    POSITIVE LOGITS
    Previous
    1.34
     Previous
    1.30
     previous
    1.27
    previous
    1.24
    PREVIOUS
    0.88
     propOrder
    0.88
     Exacts
    0.82
    annica
    0.81
     vorige
    0.78
     предыду
    0.76
    Activations Density 0.021%

    No Known Activations