© 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. 3-RES-MATRYOSHKA-DC
    7. 2717
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks

    oai_token-act-pair · gemini-2.0-flash
    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
     thank
    -0.98
     THANK
    -0.88
     useAppContext
    -0.88
     thanking
    -0.84
     Thank
    -0.81
    THANK
    -0.79
    KURZBESCHREIBUNG
    -0.79
    Thank
    -0.76
    thank
    -0.75
     thankful
    -0.74
    POSITIVE LOGITS
     u
    0.48
    者
    0.47
    <0x8F>
    0.46
    ıları
    0.46
     ор
    0.46
     πάντα
    0.46
    worte
    0.46
     inf
    0.45
    ‚¬
    0.45
     populer
    0.45
    Activations Density 0.014%

    No Known Activations