© 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. 0-CLT-HP
    7. 95195
    Prev
    Next
    INDEX
    Explanations

    eafter

    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
     ordinaria
    -0.75
     étoient
    -0.70
     auroit
    -0.68
    SBATCH
    -0.66
    ACHUSET
    -0.63
     foret
    -0.61
     étoit
    -0.61
     erupted
    -0.60
     médicale
    -0.60
     Moslem
    -0.60
    POSITIVE LOGITS
    ations
    0.68
     kasarigan
    0.65
    ings
    0.61
    uring
    0.59
    ResumeLayout
    0.59
    ening
    0.59
    BeginInit
    0.58
    als
    0.57
    ling
    0.57
    ans
    0.56
    Activations Density 1.710%

    No Known Activations