© 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. 91367
    Prev
    Next
    INDEX
    Explanations

    Wimbledon

    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
     disambiguazione
    -0.79
    AutoScaleMode
    -0.74
    LookAnd
    -0.69
    TypedDataSet
    -0.69
    BufferException
    -0.67
    rungsseite
    -0.66
     propOrder
    -0.65
     mahdol
    -0.65
    richTextPanel
    -0.65
    StoryboardSegue
    -0.64
    POSITIVE LOGITS
    mera
    0.54
    berley
    0.54
    py
    0.49
     hof
    0.47
    </thead>
    0.47
     Hof
    0.47
    berly
    0.47
     er
    0.46
    mbre
    0.46
     Hoff
    0.46
    Activations Density 0.001%

    No Known Activations