© 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. 0-CLT-HP
    7. 43444
    Prev
    Next
    INDEX
    Explanations

    technical/medical fixing processes

    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
    <bos>
    -0.65
    ↵↵
    -0.56
    k
    -0.50
    ↵
    -0.42
    ときに
    -0.40
    header
    -0.39
    n
    -0.39
     Tel
    -0.39
    kr
    -0.38
     dat
    -0.38
    POSITIVE LOGITS
    ValueStyle
    1.20
     Monfieur
    0.86
    makeConstraints
    0.84
    RenderAtEndOf
    0.84
    DockStyle
    0.82
     myſelf
    0.82
     BoxDecoration
    0.81
    :✨
    0.80
    存于互联网档案馆
    0.79
    Erreferentziak
    0.77
    Activations Density 0.085%

    No Known Activations