© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75920
    Prev
    Next
    INDEX
    Explanations

    programming code/technical documentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -0.86
     виправивши
    -0.86
    SourceChecksum
    -0.82
    GEBURTSDATUM
    -0.81
    Diwedd
    -0.81
     विश्वसनीयता
    -0.80
     ivelany
    -0.79
    StoreMessageInfo
    -0.78
    Datuak
    -0.78
    DoubleQuotes
    -0.77
    POSITIVE LOGITS
    bil
    0.42
     Lay
    0.42
     Bil
    0.41
    mul
    0.40
     Qu
    0.40
    BIL
    0.39
     bil
    0.38
     Multi
    0.37
     Mul
    0.37
    Bil
    0.37
    Activations Density 0.001%

    No Known Activations