© 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. 4-CLT-HP
    7. 1143
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ########.
    -0.66
    elemField
    -0.59
    Билгалдахарш
    -0.59
    BrowserModule
    -0.58
    CrossRef
    -0.57
    Autoritní
    -0.56
    AddHtmlAttribute
    -0.56
    bootstrapcdn
    -0.56
    Inches
    -0.54
    Portale
    -0.54
    POSITIVE LOGITS
    TagMode
    0.38
     
    0.33
    g
    0.32
     SAN
    0.31
    gan
    0.31
     san
    0.31
    gency
    0.30
    gate
    0.30
    ahu
    0.30
     El
    0.29
    Activations Density 0.016%

    No Known Activations