© 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. 5-CLT-HP
    7. 92527
    Prev
    Next
    INDEX
    Explanations

    0

    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
    DotNetBar
    -0.74
    rungsseite
    -0.71
    makeConstraints
    -0.69
    fromCharCode
    -0.69
    RECENT
    -0.68
     gestern
    -0.67
    InjectAttribute
    -0.65
    AsUp
    -0.64
    expandindo
    -0.64
     récente
    -0.63
    POSITIVE LOGITS
    Start
    0.59
    早速
    0.56
    already
    0.55
    さっそく
    0.54
     Start
    0.52
     already
    0.52
     Empieza
    0.51
     Commencez
    0.51
    Already
    0.51
    start
    0.51
    Activations Density 0.026%

    No Known Activations