© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 107
    Prev
    Next
    INDEX
    Explanations

    fml

    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
    titas
    -0.58
    Autoritní
    -0.53
    asting
    -0.50
    ZAR
    -0.49
    处
    -0.48
     Sar
    -0.47
    ucker
    -0.47
     Ac
    -0.47
    地说道
    -0.46
     Tat
    -0.46
    POSITIVE LOGITS
    AxisAlignment
    0.58
    glGen
    0.58
    MemoryWarning
    0.56
    ImageContext
    0.56
    rxjs
    0.54
    openzeppelin
    0.54
    illoin
    0.53
     ochi
    0.52
    BeginInit
    0.52
     RoutedEventArgs
    0.52
    Activations Density 0.001%

    No Known Activations