© 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. 15578
    Prev
    Next
    INDEX
    Explanations

    India

    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
    <bos>
    -1.31
    ngOnInit
    -0.46
     آذ
    -0.45
    ç
    -0.45
     estamp
    -0.43
     squee
    -0.42
     towards
    -0.42
    ClientSize
    -0.41
    ariki
    -0.41
    webElementXpaths
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.73
    ArrowToggle
    0.65
    Personendaten
    0.63
    CPtr
    0.62
     محفوظة
    0.58
     sống
    0.56
     تضيفلها
    0.56
     Nectar
    0.54
    kloped
    0.54
     Balm
    0.54
    Activations Density 0.023%

    No Known Activations