© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41518
    Prev
    Next
    INDEX
    Explanations

    Planes and mines

    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
     mine
    -0.90
    存于互联网档案馆
    -0.65
     Factbook
    -0.65
     kaynağından
    -0.65
     planes
    -0.64
     MainAxisSize
    -0.63
    IntoConstraints
    -0.62
    Билгалдахарш
    -0.61
     Program
    -0.60
    extAlignment
    -0.60
    POSITIVE LOGITS
     úgy
    0.50
     sienta
    0.50
     tecnici
    0.49
     competitivo
    0.48
     compagni
    0.47
     demek
    0.47
    Tämä
    0.47
    pole
    0.46
     negru
    0.46
     fratelli
    0.46
    Activations Density 1.497%

    No Known Activations