© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4756
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
     esternos
    -0.75
    #+#
    -0.65
    SharedDtor
    -0.62
     kasarigan
    -0.61
    writeFieldEnd
    -0.60
    Jeografia
    -0.58
    fillType
    -0.57
    AnchorStyles
    -0.57
    ValueStyle
    -0.55
    Biografi
    -0.55
    POSITIVE LOGITS
    openqa
    0.50
    ReactDOM
    0.50
    )";
    0.48
    ***************/
    0.47
    onomies
    0.46
    uarts
    0.46
     NSError
    0.45
    "]);
    0.45
    GenerationType
    0.44
    charts
    0.43
    Activations Density 0.006%

    No Known Activations