© 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. 42429
    Prev
    Next
    INDEX
    Explanations

    shapes and electrical components

    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
     religieuses
    -0.73
     vérit
    -0.69
     lèvres
    -0.69
     encroachment
    -0.68
     Seer
    -0.65
     réguli
    -0.65
     feroit
    -0.65
     varandra
    -0.64
     termica
    -0.63
     démocr
    -0.63
    POSITIVE LOGITS
     ins
    0.55
     pro
    0.52
     per
    0.50
     le
    0.46
     tri
    0.46
     IS
    0.46
     IN
    0.45
     بيها
    0.45
     all
    0.44
     US
    0.44
    Activations Density 1.138%

    No Known Activations