© 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. 20-CLT-HP
    7. 71423
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    np_max-act-logits · 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
     metres
    -0.73
    MethodManager
    -0.72
     meters
    -0.69
     Meters
    -0.69
    談社
    -0.69
    SequentialGroup
    -0.67
     sqm
    -0.66
     litres
    -0.66
    MENAFN
    -0.66
     Balls
    -0.63
    POSITIVE LOGITS
    fromnode
    0.46
    CodeAttribute
    0.45
     žel
    0.40
     Marín
    0.39
    czegó
    0.38
     case
    0.35
    arkas
    0.34
    ēd
    0.34
    ríklad
    0.33
    dillo
    0.32
    Activations Density 0.000%

    No Known Activations