© 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. 20-CLT-HP
    7. 75190
    Prev
    Next
    INDEX
    Explanations

    Off/foreign words

    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
    UnusedPrivate
    -0.68
    MemoryWarning
    -0.68
    RegressionTest
    -0.64
    SBATCH
    -0.63
    󠁢
    -0.60
    ruptedException
    -0.58
    LO
    -0.56
     nahilalakip
    -0.55
    zonego
    -0.54
    lo
    -0.54
    POSITIVE LOGITS
    verwijspagina
    0.58
    Tembelea
    0.54
     off
    0.51
    曖昧さ回避
    0.49
    rativa
    0.48
     beginnetje
    0.46
     Off
    0.45
     OFF
    0.42
    انيف
    0.42
    Off
    0.42
    Activations Density 0.000%

    No Known Activations