© 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. 1-CLT-HP
    7. 15696
    Prev
    Next
    INDEX
    Explanations

    electrical conductivity

    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
     referrerpolicy
    -0.78
     houſe
    -0.75
     conductive
    -0.74
    VersionUID
    -0.73
     myſelf
    -0.71
    ſelves
    -0.69
     Monfieur
    -0.68
     تضيفلها
    -0.66
     perfons
    -0.65
     Efq
    -0.65
    POSITIVE LOGITS
     "");
    0.49
    sh
    0.48
     pro
    0.48
     legal
    0.47
    re
    0.47
     shoot
    0.47
    imah
    0.46
     writ
    0.45
     mit
    0.45
    chit
    0.45
    Activations Density 0.007%

    No Known Activations