© 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. 4910
    Prev
    Next
    INDEX
    Explanations

    IDs and contact info

    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
    StoryboardSegue
    -0.75
     كومونز
    -0.75
     StatefulWidget
    -0.75
     AppBundle
    -0.73
    ruptedException
    -0.70
    ChildScrollView
    -0.68
     intptr
    -0.68
    TestingModule
    -0.68
     NgModule
    -0.67
    بوابة
    -0.66
    POSITIVE LOGITS
     AssemblyCulture
    0.53
     nubes
    0.53
     باخ
    0.52
     nuages
    0.51
     tecn
    0.49
     próprios
    0.47
     ifrån
    0.47
     vícti
    0.46
     difficulté
    0.45
    šanu
    0.45
    Activations Density 0.003%

    No Known Activations