© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    WriteTagHelper
    -0.77
     الحره
    -0.69
    KommentareTeilen
    -0.69
    nóstico
    -0.68
    InSection
    -0.66
     leaſt
    -0.65
    CompleteListener
    -0.63
     TextAppearance
    -0.63
     étranger
    -0.62
    withIdentifier
    -0.61
    POSITIVE LOGITS
    drawSprites
    0.46
     Esc
    0.45
    canActivate
    0.43
     Sees
    0.41
    xmlns
    0.41
    (©
    0.41
     quick
    0.40
     getM
    0.40
     Audiodateien
    0.39
     _(
    0.39
    Activations Density 0.025%

    No Known Activations