© 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. 1-CLT-HP
    7. 13770
    Prev
    Next
    INDEX
    Explanations

    technical/scientific context

    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
    IntoConstraints
    -0.73
    WriteTagHelper
    -0.72
    matum
    -0.68
    settes
    -0.67
    writeField
    -0.67
    DockStyle
    -0.67
    ErrUnexpectedEOF
    -0.66
    eneration
    -0.64
    ypeł
    -0.62
     Senhora
    -0.61
    POSITIVE LOGITS
     IActionResult
    0.52
    <bos>
    0.51
    SourceChecksum
    0.47
     />';
    0.47
    TestBed
    0.46
    __',
    0.42
    ʺ
    0.42
    ուս
    0.41
     sa
    0.41
    elerik
    0.40
    Activations Density 0.008%

    No Known Activations