© 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. 73503
    Prev
    Next
    INDEX
    Explanations

    Questions and abstracts

    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
    WindowConstants
    -0.98
    Tembelea
    -0.84
     فريبيس
    -0.76
     doInBackground
    -0.72
     BrowserModule
    -0.69
    Personendaten
    -0.69
    IntoConstraints
    -0.65
     AssemblyCompany
    -0.65
     utafitiHapana
    -0.64
    adaptiveStyles
    -0.63
    POSITIVE LOGITS
     you
    0.52
     my
    0.45
     Your
    0.41
    my
    0.40
     You
    0.40
     My
    0.39
    My
    0.38
     uve
    0.38
    chach
    0.37
    Chooser
    0.36
    Activations Density 0.000%

    No Known Activations