© 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. 94775
    Prev
    Next
    INDEX
    Explanations

    psyche

    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
    ing
    -1.10
    ity
    -0.90
    ness
    -0.82
    es
    -0.82
    y
    -0.76
    er
    -0.75
    ی
    -0.72
    al
    -0.71
    s
    -0.71
    ️
    -0.69
    POSITIVE LOGITS
    +#+#
    0.84
    GEBURTSDATUM
    0.68
     سكانية
    0.67
     Tenggara
    0.66
     nonUne
    0.64
    HtmlAttribute
    0.64
    IVEREF
    0.63
     webdriver
    0.62
    migrationBuilder
    0.60
    WireFormatLite
    0.59
    Activations Density 0.153%

    No Known Activations