© 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. 20-CLT-HP
    7. 77200
    Prev
    Next
    INDEX
    Explanations

    James

    np_max-act-logits · 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
     AssemblyProduct
    -0.79
    enderror
    -0.60
    BeginContext
    -0.54
    PCell
    -0.54
    rebbero
    -0.53
    بالإنجليزية
    -0.52
     Baillargeon
    -0.51
     MessageBoxIcon
    -0.50
    Cliff
    -0.48
     internetowa
    -0.48
    POSITIVE LOGITS
    ]")]
    0.61
    IUrlHelper
    0.60
    providedIn
    0.55
     Welles
    0.55
     дописавши
    0.52
    WithFormat
    0.50
    BASEPATH
    0.50
    ayout
    0.50
    osoever
    0.48
    actos
    0.48
    Activations Density 0.000%

    No Known Activations