© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1408
    Prev
    Next
    INDEX
    Explanations

    teaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teach
    -1.94
     teaching
    -1.78
     Teach
    -1.68
    teaching
    -1.64
    teach
    -1.63
     Teaching
    -1.61
     teaches
    -1.57
     TEACHING
    -1.57
    Teach
    -1.53
    Teaching
    -1.52
    POSITIVE LOGITS
     you
    0.64
     at
    0.55
     about
    0.52
     that
    0.52
     of
    0.51
     the
    0.48
     and
    0.48
     on
    0.48
     You
    0.47
     in
    0.47
    Activations Density 0.049%

    No Known Activations