© 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. 98021
    Prev
    Next
    INDEX
    Explanations

    computing/data

    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
     ControllerBase
    -0.65
    RegistryLite
    -0.63
     tartalomajánló
    -0.62
    ReusableCell
    -0.62
    ChildScrollView
    -0.60
    expandindo
    -0.60
     مرئيه
    -0.60
    脚注の使い方
    -0.59
     Dara
    -0.59
    ArgsConstructor
    -0.58
    POSITIVE LOGITS
     uſed
    0.57
     quæ
    0.57
    webElementXpaths
    0.54
     fubject
    0.54
     ejus
    0.54
    that
    0.53
     raiſ
    0.51
    most
    0.51
     deſt
    0.50
     eſ
    0.50
    Activations Density 0.000%

    No Known Activations