© 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. 542
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    systems
    -0.44
    assin
    -0.41
     plaats
    -0.40
    nasio
    -0.40
    estimate
    -0.39
     bén
    -0.39
     ufficiali
    -0.38
    Daphne
    -0.38
    attr
    -0.38
    TS
    -0.38
    POSITIVE LOGITS
    Vidite
    0.71
    fjspx
    0.71
     صوتيه
    0.70
     JADX
    0.67
     للمعارف
    0.66
    WithIOException
    0.66
     esternos
    0.64
    ientí
    0.64
     ErrInvalid
    0.62
     sī
    0.62
    Activations Density 0.001%

    No Known Activations