© 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. 0-CLT-HP
    7. 94076
    Prev
    Next
    INDEX
    Explanations

    Magnus

    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
    tran
    -0.52
     sac
    -0.51
    Comment
    -0.47
    ESA
    -0.44
    keto
    -0.44
    comments
    -0.43
    lasyon
    -0.43
     cul
    -0.43
    eventbus
    -0.43
     Sam
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    1.02
     ―――――
    0.96
    IsContent
    0.95
     myſelf
    0.93
     Houſe
    0.90
     itſelf
    0.87
    TagMode
    0.86
     étoit
    0.86
     Reſ
    0.85
     houſe
    0.85
    Activations Density 0.447%

    No Known Activations