© 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. 1-CLT-HP
    7. 10032
    Prev
    Next
    INDEX
    Explanations

    teachers

    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
     Roskov
    -1.02
     Teachers
    -0.98
    teachers
    -0.94
    UnsafeEnabled
    -0.94
    Teachers
    -0.93
     teacher
    -0.93
     teachers
    -0.92
     myſelf
    -0.91
    teacher
    -0.88
     Teacher
    -0.86
    POSITIVE LOGITS
    ↵
    0.45
     pro
    0.41
    ,
    0.39
    He
    0.38
    #
    0.37
    ’
    0.37
    .
    0.36
     
    0.36
    ondra
    0.36
     pan
    0.35
    Activations Density 0.003%

    No Known Activations