© 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. 1-CLT-HP
    7. 10700
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     ko
    -0.44
    ⓘ
    -0.39
    ılıyor
    -0.39
     "
    -0.39
     Ko
    -0.38
     Familienname
    -0.36
     (
    -0.36
    run
    -0.36
    greifen
    -0.36
     run
    -0.35
    POSITIVE LOGITS
     itſelf
    0.97
    ſelves
    0.93
     Jefus
    0.93
     Efq
    0.92
     Houſe
    0.92
     houſe
    0.91
    ſelf
    0.88
     متعلقه
    0.88
     Majefty
    0.87
     doubtnut
    0.86
    Activations Density 0.008%

    No Known Activations