© 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. 14518
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    ftagPool
    -0.59
    ⓧ
    -0.53
     scolaires
    -0.53
    blå
    -0.50
    其他的
    -0.50
    UVWXYZ
    -0.50
     môžu
    -0.50
     digitais
    -0.49
    IRUS
    -0.48
    他の
    -0.48
    POSITIVE LOGITS
     חיצוניים
    0.59
     BufferedWriter
    0.59
    __':
    0.59
     المعيارى
    0.57
    AddHtmlAttribute
    0.57
    ᅠ
    0.56
     frow
    0.56
    ěř
    0.56
     跳转至
    0.55
     للمعارف
    0.54
    Activations Density 0.321%

    No Known Activations