© 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. 4-CLT-HP
    7. 458
    Prev
    Next
    INDEX
    Explanations

    course

    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
     avoient
    -0.75
     uſed
    -0.69
     himſelf
    -0.67
     poffible
    -0.66
     juſ
    -0.66
    енча
    -0.65
     myſelf
    -0.65
     raiſ
    -0.65
    middels
    -0.64
     ſhe
    -0.63
    POSITIVE LOGITS
     of
    0.77
    TypedDataSet
    0.64
     curriculum
    0.63
    work
    0.60
     lectures
    0.60
     courses
    0.59
    load
    0.59
     study
    0.58
     load
    0.58
     work
    0.58
    Activations Density 0.004%

    No Known Activations