© 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. 4-CLT-HP
    7. 1313
    Prev
    Next
    INDEX
    Explanations

    inge

    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
     détru
    -0.32
     oike
    -0.31
     matang
    -0.31
     agujas
    -0.29
    gib
    -0.29
     Überg
    -0.28
     empfohlen
    -0.28
    ade
    -0.28
    age
    -0.27
    ellschaft
    -0.27
    POSITIVE LOGITS
    ########.
    0.93
    تقاوى
    0.88
    ंदीखरीदारी
    0.86
     surla
    0.86
    ReusableCell
    0.86
    BeginContext
    0.85
     مشين
    0.85
    aarrggbb
    0.84
    مصادر
    0.83
     protoimpl
    0.82
    Activations Density 0.004%

    No Known Activations