© 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. 91319
    Prev
    Next
    INDEX
    Explanations

    Cub

    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
    PMailer
    -0.72
    AddTagHelper
    -0.66
     initComponents
    -0.60
    ValueStyle
    -0.57
    riwal
    -0.56
    SBATCH
    -0.55
    Indust
    -0.54
    mybatisplus
    -0.54
    __":
    -0.53
    migrationBuilder
    -0.53
    POSITIVE LOGITS
     محفوظة
    0.58
     Kauf
    0.58
     metav
    0.52
    Kauf
    0.48
    freopen
    0.48
     censiti
    0.46
     répar
    0.45
    au
    0.44
    InputBorder
    0.44
    of
    0.43
    Activations Density 0.001%

    No Known Activations