© 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. 5229
    Prev
    Next
    INDEX
    Explanations

    down

    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
    脚注の使い方
    -0.52
     חיצוניים
    -0.52
     beat
    -0.51
    发表于
    -0.47
    <bos>
    -0.45
    beat
    -0.45
    Sw
    -0.42
     assisti
    -0.41
     meet
    -0.41
     solve
    -0.41
    POSITIVE LOGITS
    TestingModule
    0.71
     Hivatalos
    0.71
     noqa
    0.69
    EDEFAULT
    0.67
    Παραπομπές
    0.67
     to
    0.67
     anteriore
    0.64
     незавершена
    0.63
    BeginContext
    0.62
    multer
    0.61
    Activations Density 0.021%

    No Known Activations