© 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. 92475
    Prev
    Next
    INDEX
    Explanations

    mazes and complex systems

    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
     fit
    -0.50
     deck
    -0.45
    nya
    -0.43
     fights
    -0.41
    entis
    -0.41
     docking
    -0.41
     song
    -0.40
    SignedIn
    -0.40
     True
    -0.40
     phù
    -0.39
    POSITIVE LOGITS
     المعيارى
    0.78
    InputBorder
    0.75
    ChildScrollView
    0.72
     وتسجيلات
    0.68
    ädie
    0.68
     typelib
    0.65
    ine
    0.63
    saraba
    0.61
     quæ
    0.59
    UnknownFields
    0.59
    Activations Density 0.001%

    No Known Activations