© 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. 5-CLT-HP
    7. 5744
    Prev
    Next
    INDEX
    Explanations

    the

    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
    مصادر
    -0.52
     StatelessWidget
    -0.44
    com
    -0.43
     layui
    -0.43
     Kein
    -0.41
     дописавши
    -0.40
    меч
    -0.40
     resembled
    -0.39
     went
    -0.38
    Mailer
    -0.38
    POSITIVE LOGITS
     وتسجيلات
    0.62
    ContentAlignment
    0.60
    orses
    0.58
    исленность
    0.58
     الحره
    0.58
    RectangleBorder
    0.58
    InjectAttribute
    0.57
     виправивши
    0.57
    (!__
    0.57
    Portale
    0.56
    Activations Density 0.002%

    No Known Activations