© 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. 5-CLT-HP
    7. 97106
    Prev
    Next
    INDEX
    Explanations

    describes processes and capabilities

    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
    vende
    -0.44
     CreateTagHelper
    -0.41
    存于互联网档案馆
    -0.39
    addHandler
    -0.38
    ►
    -0.38
    keletal
    -0.38
     Bend
    -0.37
    uro
    -0.36
    entrySet
    -0.36
    ombi
    -0.36
    POSITIVE LOGITS
     autorytatywna
    1.00
    AddTagHelper
    0.91
    XmlAccessType
    0.87
    awtextra
    0.86
    SharedCtor
    0.85
    findpost
    0.84
     GenerationType
    0.84
    GEBURTSDATUM
    0.82
    ніципа
    0.78
    Autoritní
    0.75
    Activations Density 0.001%

    No Known Activations