© 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. 91857
    Prev
    Next
    INDEX
    Explanations

    careers

    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
    ί
    -0.44
     liberi
    -0.44
     eller
    -0.44
    市
    -0.43
    тру
    -0.43
    ním
    -0.43
    libros
    -0.43
     valle
    -0.43
     evangé
    -0.43
     Técnica
    -0.42
    POSITIVE LOGITS
    UrlResolution
    0.71
    MLLoader
    0.69
    ConstraintMaker
    0.68
     فريبيس
    0.66
     Normdatei
    0.64
    fromCharCode
    0.62
    الحياه
    0.62
    criminator
    0.60
    Geplaatst
    0.59
    mbggenerated
    0.59
    Activations Density 0.002%

    No Known Activations