© 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. 75791
    Prev
    Next
    INDEX
    Explanations

    large/significant

    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
    GEBURTSDATUM
    -1.05
     snippetHide
    -1.05
     utafitiHapana
    -0.91
     ainfi
    -0.90
    تقاوى
    -0.90
     autorité
    -0.86
     scolaires
    -0.85
    tvguidetime
    -0.84
    GraphicsUnit
    -0.84
    ArrowToggle
    -0.84
    POSITIVE LOGITS
     share
    0.86
     section
    0.69
     segment
    0.69
     portion
    0.66
     percentage
    0.65
     proportion
    0.64
     part
    0.63
     per
    0.62
     chunk
    0.59
     sw
    0.57
    Activations Density 0.005%

    No Known Activations