© 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. 5100
    Prev
    Next
    INDEX
    Explanations

    sentence fragments

    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
    oa̍t
    -0.60
    exitRule
    -0.60
     resourceCulture
    -0.59
    MigrationBuilder
    -0.58
     ddelweddau
    -0.57
    webElementXpaths
    -0.55
    apimachinery
    -0.54
     isComment
    -0.54
    Geplaatst
    -0.53
    WithEmail
    -0.52
    POSITIVE LOGITS
     he
    0.76
     alimentaires
    0.58
     виправивши
    0.57
     hän
    0.54
     konge
    0.53
     vanligt
    0.52
    himself
    0.51
     он
    0.51
     aisladas
    0.51
     nào
    0.50
    Activations Density 0.000%

    No Known Activations