© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8705
    Prev
    Next
    INDEX
    Explanations

    really

    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
    Negative Logits
     leaſt
    -0.63
     purpoſe
    -0.55
     becauſe
    -0.54
    сылкі
    -0.54
     credere
    -0.52
     podí
    -0.52
    kasten
    -0.51
     Nacionales
    -0.51
    Архівовано
    -0.50
     ſte
    -0.50
    POSITIVE LOGITS
    IsContent
    0.54
    SequentialGroup
    0.52
    //
    0.47
    antaine
    0.47
    asche
    0.46
    brać
    0.46
     usos
    0.45
    انجليز
    0.45
     utafitiHapana
    0.45
    onOptions
    0.45
    Activations Density 0.100%

    No Known Activations