© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93855
    Prev
    Next
    INDEX
    Explanations

    science/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
    5
    -0.39
    ff
    -0.37
     seniors
    -0.36
    6
    -0.35
     H
    -0.34
     eti
    -0.34
     area
    -0.34
    <bos>
    -0.34
     sá
    -0.34
    LinkId
    -0.34
    POSITIVE LOGITS
    MigrationBuilder
    0.88
    mybatisplus
    0.85
    ValueStyle
    0.82
    NOPQRST
    0.82
     chrétiens
    0.82
     Infórmanos
    0.77
     quelquefois
    0.77
     Monfieur
    0.76
     myſelf
    0.76
     Grecs
    0.76
    Activations Density 0.000%

    No Known Activations