© 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. 77235
    Prev
    Next
    INDEX
    Explanations

    "un" and "mono" prefixes

    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
    NameInMap
    -0.82
     Administrativna
    -0.78
    WebServlet
    -0.77
    DeleteBehavior
    -0.73
    RenderAtEndOf
    -0.64
     unknownFields
    -0.64
    ρους
    -0.60
    plr
    -0.60
    JspWriter
    -0.60
     FormBuilder
    -0.59
    POSITIVE LOGITS
     un
    0.66
     mono
    0.63
    un
    0.56
    mono
    0.54
     McPherson
    0.54
     Un
    0.53
    Un
    0.52
     Mono
    0.50
     under
    0.50
    Mono
    0.46
    Activations Density 0.000%

    No Known Activations