© 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. 71384
    Prev
    Next
    INDEX
    Explanations

    are

    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
     Serving
    -0.78
    Serving
    -0.75
    FieldDescriptor
    -0.75
     ExecuteAsync
    -0.73
     attravers
    -0.69
     Normdatei
    -0.68
     defStyleAttr
    -0.67
     répartition
    -0.65
     jouant
    -0.65
     mattino
    -0.64
    POSITIVE LOGITS
     available
    0.52
     supplied
    0.48
    ophilia
    0.48
     offered
    0.48
    斯坦
    0.43
     clear
    0.43
     avail
    0.43
     stable
    0.41
     nonatomic
    0.41
    reactivex
    0.40
    Activations Density 0.002%

    No Known Activations