© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "full" used with high confidence

    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
    Completely
    -1.35
    Complete
    -1.33
     Complete
    -1.31
     Completely
    -1.31
     completes
    -1.28
     COMPLE
    -1.28
    complete
    -1.24
     completely
    -1.23
     COMPLETE
    -1.23
    COMPLE
    -1.22
    POSITIVE LOGITS
     full
    2.89
     Full
    2.73
    full
    2.72
    Full
    2.67
    FULL
    2.27
     FULL
    2.14
     pleine
    1.45
     vollen
    1.39
    フル
    1.38
     フル
    1.37
    Activations Density 0.198%

    No Known Activations