© 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. 4415
    Prev
    Next
    INDEX
    Explanations

    decimal points in text

    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
     Fig
    -1.30
    Fig
    -1.21
    fig
    -1.16
     fig
    -1.04
    SharedCtor
    -0.91
     Figs
    -0.90
    Figs
    -0.88
    FIG
    -0.86
    DIPSETTING
    -0.73
     FIG
    -0.70
    POSITIVE LOGITS
    ftagPool
    0.55
     aéri
    0.52
     ***!
    0.51
     small
    0.51
    즈
    0.51
    namic
    0.50
    small
    0.49
     compagni
    0.48
    namese
    0.48
     honn
    0.48
    Activations Density 0.051%

    No Known Activations