© 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. 72649
    Prev
    Next
    INDEX
    Explanations

    Technical texts

    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
    SourceChecksum
    -0.91
    UnusedPrivate
    -0.85
     kasarigan
    -0.84
    ьаж
    -0.79
    ArrowToggle
    -0.79
     ویکی‌پدی
    -0.78
    Datuak
    -0.77
    DockStyle
    -0.77
     Roskov
    -0.76
     nakalista
    -0.75
    POSITIVE LOGITS
     hard
    0.73
     in
    0.70
     on
    0.68
     job
    0.64
    hard
    0.55
     In
    0.49
     On
    0.49
    on
    0.49
    Hard
    0.48
     Hard
    0.48
    Activations Density 0.000%

    No Known Activations