© 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. 97505
    Prev
    Next
    INDEX
    Explanations

    politics/news

    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
     nakalista
    -0.82
    Tikang
    -0.73
     complètes
    -0.70
     stället
    -0.70
    parsedMessage
    -0.69
     băr
    -0.67
    mybatisplus
    -0.67
    futbolista
    -0.66
     scolaires
    -0.66
     artificiales
    -0.65
    POSITIVE LOGITS
     n
    0.44
     adu
    0.42
     intest
    0.40
    SequentialGroup
    0.39
     الاطلاع
    0.39
     custom
    0.38
     fea
    0.37
     coun
    0.37
     avis
    0.37
     condes
    0.36
    Activations Density 0.005%

    No Known Activations