© 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. 1-CLT-HP
    7. 9528
    Prev
    Next
    INDEX
    Explanations

    Dumas

    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
     Dumas
    -1.52
    IntoConstraints
    -0.76
    atification
    -0.68
    tagHelperRunner
    -0.67
     lenker
    -0.63
    rxjs
    -0.60
     >=",
    -0.58
     OFDb
    -0.57
    MemoryWarning
    -0.57
    Portale
    -0.55
    POSITIVE LOGITS
    Pseudo
    0.55
    MenuView
    0.50
     practi
    0.50
     McKenzie
    0.49
     réfugi
    0.49
     Prefecture
    0.48
     kef
    0.48
    médiaire
    0.48
    endcsname
    0.47
     Pseudo
    0.47
    Activations Density 0.022%

    No Known Activations