© 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. 4-CLT-HP
    7. 1818
    Prev
    Next
    INDEX
    Explanations

    science, medicine

    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
    Ārējās
    -0.76
    Diweddarwch
    -0.70
    Portail
    -0.67
    帖最后由
    -0.67
    cèse
    -0.65
     محفوظة
    -0.65
    VIAF
    -0.60
     OFDb
    -0.59
     '\\;'
    -0.59
    PreferredItem
    -0.58
    POSITIVE LOGITS
    Fletcher
    0.52
    vician
    0.50
    rif
    0.50
     Fletcher
    0.50
     ComVisible
    0.49
     DIEGO
    0.48
    BURGH
    0.47
    Wut
    0.47
     Faso
    0.47
    GetField
    0.47
    Activations Density 0.005%

    No Known Activations