© 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. 20-CLT-HP
    7. 72420
    Prev
    Next
    INDEX
    Explanations

    the

    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
     فريبيس
    -1.01
    IContainer
    -0.77
    UnusedPrivate
    -0.67
    IntoConstraints
    -0.63
    Datuak
    -0.63
    hésite
    -0.63
    CrossRef
    -0.63
     FontFamily
    -0.61
    indrical
    -0.59
    MemoryWarning
    -0.59
    POSITIVE LOGITS
     major
    0.56
     rate
    0.54
     terminal
    0.52
    下载附件
    0.52
    arf
    0.50
     termin
    0.48
    rate
    0.47
    Exclu
    0.46
     exclusive
    0.44
     minimal
    0.43
    Activations Density 0.002%

    No Known Activations