© 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. 93669
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    ↵
    -0.62
    1
    -0.62
    5
    -0.61
    6
    -0.60
    4
    -0.58
    7
    -0.54
    9
    -0.52
    यन
    -0.49
    Cubit
    -0.49
    3
    -0.47
    POSITIVE LOGITS
    GEBURTS
    0.69
     disambiguazione
    0.68
    AnimationsModule
    0.66
    脚注の使い方
    0.66
    ChildScrollView
    0.64
     Audiodateien
    0.61
     CreateTagHelper
    0.60
    CloseOperation
    0.60
    NewLabel
    0.60
    AxisAlignment
    0.59
    Activations Density 0.001%

    No Known Activations