© 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. 5-CLT-HP
    7. 3377
    Prev
    Next
    INDEX
    Explanations

    in/living

    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
    Personendaten
    -0.63
    tagHelperRunner
    -0.55
    EditorBrowsable
    -0.54
    )";
    -0.51
    AccessorTable
    -0.51
    ValueStyle
    -0.50
    theoremstyle
    -0.50
    RTLD
    -0.48
    JAXB
    -0.47
    resave
    -0.47
    POSITIVE LOGITS
    addCriterion
    0.62
    enty
    0.57
     Outdoors
    0.56
     utafitiHapana
    0.52
    gelijk
    0.51
     Himo
    0.51
     dne
    0.50
    oredCriteria
    0.50
    arası
    0.50
    InView
    0.50
    Activations Density 0.002%

    No Known Activations