© 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. 97775
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
     متعلقه
    -0.71
    ///</
    -0.69
     Efq
    -0.63
     Eſ
    -0.61
     pleaſure
    -0.57
    TagMode
    -0.57
    prnewswire
    -0.56
     GenerationType
    -0.56
     Acting
    -0.56
    IUrlHelper
    -0.54
    POSITIVE LOGITS
    6
    0.72
    2
    0.67
    1
    0.65
    9
    0.62
    3
    0.62
    5
    0.60
    4
    0.57
    7
    0.56
    8
    0.56
    0
    0.53
    Activations Density 0.001%

    No Known Activations