© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    air

    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
    .
    -0.61
     TestBed
    -0.59
     as
    -0.56
    .;
    -0.56
     in
    -0.56
     unless
    -0.54
     fédé
    -0.54
     so
    -0.50
     to
    -0.49
     because
    -0.49
    POSITIVE LOGITS
     تانيه
    0.74
    حياته
    0.65
     surla
    0.63
     الحره
    0.63
    ThroughAttribute
    0.56
     خاصية
    0.55
     purpoſe
    0.55
    __':
    0.55
     serves
    0.55
    NUMX
    0.55
    Activations Density 0.080%

    No Known Activations