© 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. 92543
    Prev
    Next
    INDEX
    Explanations

    database searches

    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
     Monfieur
    -0.61
     ſeveral
    -0.61
     Inſ
    -0.60
     ſmall
    -0.60
     Diſ
    -0.59
     EconPapers
    -0.57
     search
    -0.57
    diac
    -0.56
    IntoConstraints
    -0.56
     pleaſure
    -0.56
    POSITIVE LOGITS
     محفوظة
    0.56
    ImageContext
    0.51
    WebControls
    0.50
     neki
    0.50
    下载附件
    0.49
     for
    0.49
    glVertex
    0.48
    numerusform
    0.47
    rrggbb
    0.47
    出版年
    0.47
    Activations Density 0.010%

    No Known Activations