© 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. 5-CLT-HP
    7. 2889
    Prev
    Next
    INDEX
    Explanations

    Ordinal suffixes

    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
     ['./
    -0.56
     Oppenheimer
    -0.51
    čít
    -0.46
    ετε
    -0.45
     vies
    -0.45
     Rajiv
    -0.44
     Governor
    -0.44
    laszt
    -0.43
    tschaft
    -0.43
     interpr
    -0.42
    POSITIVE LOGITS
    saraba
    0.63
    Personendaten
    0.62
    Demografia
    0.61
    extAlignment
    0.60
    volts
    0.59
    ftagPool
    0.59
    Personensuche
    0.54
    页面存档备份
    0.54
    optionalTypeArgs
    0.53
     لينك
    0.52
    Activations Density 0.002%

    No Known Activations