© 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. 5-CLT-HP
    7. 92610
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    rawDesc
    -0.62
    abestanden
    -0.60
     étoient
    -0.58
    MigrationBuilder
    -0.58
    Referências
    -0.57
     Normdatei
    -0.56
    adaptiveStyles
    -0.56
    actionMode
    -0.55
    apimachinery
    -0.54
     camadas
    -0.53
    POSITIVE LOGITS
    mybatisplus
    0.67
     rest
    0.56
    rest
    0.55
     principal
    0.52
     by
    0.52
    ins
    0.50
    w
    0.49
    ort
    0.49
    ble
    0.48
     remains
    0.48
    Activations Density 0.000%

    No Known Activations