© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9756
    Prev
    Next
    INDEX
    Explanations

    Filipino language/Philippines

    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
    PreferredItem
    -0.79
     referenties
    -0.63
     विश्वसनीयता
    -0.61
    ніципа
    -0.59
    PerformLayout
    -0.57
    Rome
    -0.56
     dAtA
    -0.56
    estinian
    -0.56
    Brainz
    -0.55
     Rome
    -0.55
    POSITIVE LOGITS
     pinulongan
    0.59
     ang
    0.51
    alang
    0.49
    angan
    0.48
     critères
    0.46
     transfieras
    0.46
     AsyncTask
    0.45
     élevés
    0.45
    ButterKnife
    0.45
    LONG
    0.44
    Activations Density 0.020%

    No Known Activations