© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16174
    Prev
    Next
    INDEX
    Explanations

    physics

    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
    Negative Logits
     estri
    -0.54
    stava
    -0.53
    irchen
    -0.48
    สึก
    -0.46
     图库
    -0.45
     symbiotic
    -0.44
    ptest
    -0.44
    logous
    -0.44
    bral
    -0.44
     oscillatory
    -0.44
    POSITIVE LOGITS
     برانيه
    0.66
    nocześnie
    0.63
    Personendaten
    0.59
    новништво
    0.57
    olingo
    0.56
    İstinadlar
    0.55
     "..\..\
    0.55
    CPtr
    0.54
     vitesses
    0.53
    setCellValue
    0.53
    Activations Density 0.041%

    No Known Activations