© 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. 5-CLT-HP
    7. 6083
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    \{\\
    -0.77
    borderSide
    -0.67
     GetEnumerator
    -0.64
    IntoConstraints
    -0.62
     дописавши
    -0.61
    NewUrlParser
    -0.60
    MethodManager
    -0.60
    GraphicsUnit
    -0.60
    TargetException
    -0.60
     ComVisible
    -0.58
    POSITIVE LOGITS
    2
    0.71
    oneofs
    0.60
    1
    0.57
    izard
    0.50
    ucht
    0.49
    hazi
    0.49
     accro
    0.49
     Muda
    0.48
     vys
    0.47
    owicz
    0.47
    Activations Density 0.008%

    No Known Activations