© 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. 5559
    Prev
    Next
    INDEX
    Explanations

    system

    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
     process
    -0.66
    ///</
    -0.64
     Doing
    -0.63
    process
    -0.59
    Datuak
    -0.58
     doing
    -0.57
     procedure
    -0.56
     procédure
    -0.54
    Étape
    -0.54
    doing
    -0.53
    POSITIVE LOGITS
     mergeFrom
    0.71
     kasarigan
    0.66
    fxml
    0.55
     propOrder
    0.55
    exitRule
    0.55
    ErrUnexpectedEOF
    0.53
    UpInside
    0.52
     viewDidLoad
    0.52
     gorges
    0.52
    viewDidLoad
    0.51
    Activations Density 0.002%

    No Known Activations