© 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. 8926
    Prev
    Next
    INDEX
    Explanations

    scientific or technical contexts

    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
    infrared
    -1.32
     poveznice
    -0.54
    ist
    -0.50
     patří
    -0.50
     nahilalakip
    -0.49
    Infrared
    -0.48
     Normdatei
    -0.48
    verwijspagina
    -0.47
    ריס
    -0.46
    ized
    -0.44
    POSITIVE LOGITS
    StructEnd
    0.75
     PackageManager
    0.71
    AxisAlignment
    0.71
    /*
    0.65
    Getenv
    0.62
    ſelf
    0.61
     Meksiku
    0.60
     SDLK
    0.60
    encodeWith
    0.59
     prede
    0.59
    Activations Density 0.041%

    No Known Activations