© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    liquid

    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
    kloped
    -0.85
     kaarangay
    -0.82
     transfieras
    -0.81
    Vidite
    -0.79
    MessageTagHelper
    -0.77
    nthesis
    -0.75
    ennifer
    -0.73
    MigrationBuilder
    -0.73
    InputBorder
    -0.73
    virons
    -0.70
    POSITIVE LOGITS
    at
    0.46
     spo
    0.45
    simos
    0.44
    .
    0.44
    so
    0.43
     long
    0.43
    ler
    0.41
    raw
    0.40
    all
    0.40
    se
    0.40
    Activations Density 0.239%

    No Known Activations