© 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. 43070
    Prev
    Next
    INDEX
    Explanations

    genetics and neurology

    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
     remote
    -0.86
     télécommande
    -0.80
     CHARLES
    -0.78
     charles
    -0.75
    Charles
    -0.73
    PR
    -0.72
     cérami
    -0.69
     espagne
    -0.69
    cals
    -0.68
     jouets
    -0.68
    POSITIVE LOGITS
     المعيارى
    0.65
     Ast
    0.60
     uintptr
    0.57
    SBATCH
    0.57
    rinfo
    0.56
    PerformLayout
    0.55
    <_>
    0.54
    WriteBarrier
    0.53
     native
    0.52
     Sider
    0.52
    Activations Density 0.124%

    No Known Activations