© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    frequent occurrence references

    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
     normally
    -1.34
    normally
    -1.32
     ordinarily
    -1.29
     Normally
    -1.20
     normalerweise
    -1.18
     normalement
    -1.17
    Normally
    -1.15
    generally
    -1.15
     generally
    -1.11
     typically
    -1.09
    POSITIVE LOGITS
     often
    1.41
     Often
    1.19
    often
    1.16
    Often
    1.13
     frequently
    1.11
     menudo
    1.02
     oft
    0.98
     часто
    0.98
     frequent
    0.96
     sering
    0.90
    Activations Density 0.039%

    No Known Activations