© 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. 1-CLT-HP
    7. 10316
    Prev
    Next
    INDEX
    Explanations

    desire, deprivation

    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
     Desire
    -0.76
    Desire
    -0.72
    coming
    -0.70
    ofire
    -0.70
    ագրություններ
    -0.68
    vings
    -0.68
    AddField
    -0.64
    WriteBarrier
    -0.64
    UrlResolution
    -0.63
    phalt
    -0.63
    POSITIVE LOGITS
     TextAppearance
    0.52
    kosi
    0.50
    subpackage
    0.46
    severity
    0.46
     modest
    0.45
     Magno
    0.44
     Speise
    0.44
     Crossword
    0.44
     skjø
    0.43
     lemn
    0.43
    Activations Density 0.011%

    No Known Activations