© 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. 20-CLT-HP
    7. 75441
    Prev
    Next
    INDEX
    Explanations

    Technical/code snippets

    np_max-act-logits · 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
     typelib
    -0.76
     يتيمه
    -0.75
     Wiktionnaire
    -0.73
     فريبيس
    -0.72
    AutoresizingMask
    -0.71
    IVEREF
    -0.71
    expandindo
    -0.70
     كومونز
    -0.70
     viewDidLoad
    -0.69
    twimg
    -0.69
    POSITIVE LOGITS
     riso
    0.42
    gy
    0.41
     ब्रेकडाउन
    0.40
    ky
    0.40
    нове
    0.39
    oy
    0.39
    ApiModel
    0.39
    E
    0.39
    Latest
    0.38
     Âu
    0.38
    Activations Density 0.010%

    No Known Activations