© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     CreateTagHelper
    -0.92
     wards
    -0.62
    Lähteet
    -0.60
     pumps
    -0.60
    UnknownFields
    -0.59
    __*/
    -0.57
     flaps
    -0.56
     stadiums
    -0.56
     alloys
    -0.56
    stdc
    -0.55
    POSITIVE LOGITS
    DockStyle
    0.55
     للاسماء
    0.51
     "..\..\..\
    0.49
    CloseOperation
    0.48
     Италијани
    0.48
    nější
    0.48
    ghouse
    0.47
     TextAppearance
    0.47
     يتيمه
    0.47
     decent
    0.45
    Activations Density 0.004%

    No Known Activations