© 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. 1-CLT-HP
    7. 592
    Prev
    Next
    INDEX
    Explanations

    Ordinal 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
     tetra
    -0.72
     IV
    -0.71
    fourth
    -0.67
    发表于
    -0.66
    djangoproject
    -0.64
    клопе
    -0.62
    IV
    -0.60
    四
    -0.60
    audiovisuel
    -0.57
    Referencie
    -0.57
    POSITIVE LOGITS
    ranslated
    0.52
    InvalidProtocol
    0.52
    titled
    0.48
     Satin
    0.47
    atista
    0.46
     سكانية
    0.46
     penalties
    0.46
     deeds
    0.46
    scrollbar
    0.46
    ext
    0.46
    Activations Density 0.022%

    No Known Activations