© 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. 1-CLT-HP
    7. 14501
    Prev
    Next
    INDEX
    Explanations

    dressing

    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
     sari
    -0.90
    ParallelGroup
    -0.67
     saree
    -0.65
     kasarigan
    -0.65
     Sari
    -0.57
    ngrx
    -0.54
     sarees
    -0.52
     Sare
    -0.48
    Kjelder
    -0.47
    HasIndex
    -0.44
    POSITIVE LOGITS
     referenties
    0.68
    UIControlState
    0.64
     متعلقه
    0.60
    fromnode
    0.59
    tagext
    0.57
    WireFormatLite
    0.55
    parsedMessage
    0.55
    LayoutStyle
    0.55
    ")));
    0.54
    RegressionTest
    0.53
    Activations Density 0.022%

    No Known Activations