© 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. 20-CLT-HP
    7. 76899
    Prev
    Next
    INDEX
    Explanations

    Rare words

    np_max-act-logits · 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
    évaluateur
    -0.56
    ArgumentParser
    -0.56
    MessageTagHelper
    -0.55
    Personendaten
    -0.51
    ✭✭
    -0.51
     referenties
    -0.50
    astéroïdes
    -0.48
     pinulongan
    -0.44
     Anfitrión
    -0.43
    afone
    -0.43
    POSITIVE LOGITS
    EndContext
    0.60
    transQ
    0.55
    gts
    0.54
    mk
    0.53
    нского
    0.52
    Amérique
    0.52
     ду
    0.50
     door
    0.50
    нский
    0.50
    gs
    0.50
    Activations Density 0.007%

    No Known Activations