© 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. 5-CLT-HP
    7. 91881
    Prev
    Next
    INDEX
    Explanations

    years

    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
     logo
    -0.44
     commonly
    -0.42
     you
    -0.42
    :"
    -0.41
    iência
    -0.40
     sometimes
    -0.39
    ikt
    -0.38
     personality
    -0.37
     encounter
    -0.37
     pros
    -0.37
    POSITIVE LOGITS
    UserScript
    0.90
    ftagPool
    0.82
    Personendaten
    0.81
     propOrder
    0.79
     autorytatywna
    0.78
    rawDesc
    0.77
    XmlAccessType
    0.74
     '\\;'
    0.73
    ArrowToggle
    0.73
    aarrggbb
    0.73
    Activations Density 0.003%

    No Known Activations