© 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. 4-CLT-HP
    7. 2071
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    aarrggbb
    -0.54
    Véxase
    -0.54
     împreună
    -0.52
     enjeux
    -0.51
    الإنجليزية
    -0.50
     وتسجيلات
    -0.50
     amarillas
    -0.50
     emprego
    -0.50
     impegno
    -0.49
    esModule
    -0.49
    POSITIVE LOGITS
    autique
    0.64
     top
    0.63
     bezeichneter
    0.60
     Италијани
    0.56
     SwitchCompat
    0.55
     Things
    0.55
    lovakia
    0.54
    ngOn
    0.53
     تضيفلها
    0.52
    PHONY
    0.52
    Activations Density 0.008%

    No Known Activations