© 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. 5-CLT-HP
    7. 97284
    Prev
    Next
    INDEX
    Explanations

    news and reporting

    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
     gyhoeddwyd
    -0.63
    batore
    -0.62
     gynhyrchwyd
    -0.61
    eleste
    -0.60
     Escolar
    -0.59
     referrerpolicy
    -0.59
    الحياه
    -0.59
    HideFlags
    -0.57
    pozdrawiam
    -0.57
    NotFoundError
    -0.56
    POSITIVE LOGITS
     news
    0.64
     News
    0.56
    news
    0.50
     media
    0.50
    News
    0.49
    zeera
    0.49
     periodistas
    0.49
    arraycopy
    0.48
     journalists
    0.48
    magazine
    0.46
    Activations Density 0.000%

    No Known Activations