© 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. 4-CLT-HP
    7. 355
    Prev
    Next
    INDEX
    Explanations

    pregnancy

    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
     recognition
    -0.56
     rechange
    -0.48
     warfare
    -0.47
    recognition
    -0.46
    oredCriteria
    -0.45
    ity
    -0.45
     Warfare
    -0.43
     smrti
    -0.42
    Brig
    -0.42
    Junction
    -0.41
    POSITIVE LOGITS
    EndInit
    0.76
    chromedriver
    0.69
    曖昧さ回避
    0.63
    dirond
    0.61
    StoredProcedure
    0.60
    verwijspagina
    0.60
    existsSync
    0.59
     kasarigan
    0.59
    +#+#
    0.59
     viewDidLoad
    0.58
    Activations Density 0.001%

    No Known Activations