© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    nier

    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
    ing
    -1.13
    ING
    -0.74
    ת
    -0.61
    ة
    -0.55
    ingos
    -0.52
     aux
    -0.49
    en
    -0.46
    ć
    -0.44
    ть
    -0.43
    て
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.97
     تضيفلها
    0.94
     Infórmanos
    0.90
     beginnetje
    0.89
    verwijspagina
    0.85
    ftagPool
    0.85
    aarrggbb
    0.85
    Tikang
    0.85
     ostavi
    0.84
     Anſ
    0.84
    Activations Density 1.270%

    No Known Activations