© 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. 97539
    Prev
    Next
    INDEX
    Explanations

    Describing two entities

    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
    KommentareTeilen
    -0.75
    esez
    -0.53
     zä
    -0.46
     fatta
    -0.45
     Outside
    -0.43
    tik
    -0.42
    outside
    -0.41
    //
    -0.41
    bon
    -0.41
     mergeFrom
    -0.41
    POSITIVE LOGITS
    بوابة
    0.73
    Datuak
    0.72
    webElementXpaths
    0.62
    UniformLocation
    0.61
    MessageTagHelper
    0.61
     feel
    0.60
     heirs
    0.59
    DockStyle
    0.59
     realise
    0.59
     realize
    0.58
    Activations Density 0.010%

    No Known Activations