© 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. 5-CLT-HP
    7. 93316
    Prev
    Next
    INDEX
    Explanations

    com

    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
    RegressionTest
    -0.69
    ########.
    -0.66
     للمعارف
    -0.65
    bootstrapcdn
    -0.64
    ValueStyle
    -0.63
    rungsseite
    -0.61
     ostavi
    -0.60
    StructEnd
    -0.60
    posedge
    -0.57
    richTextPanel
    -0.57
    POSITIVE LOGITS
     BorderRadius
    0.49
     pisau
    0.48
    operazione
    0.46
     feet
    0.46
     regional
    0.46
     attentive
    0.45
     operations
    0.45
    aderno
    0.44
     gracious
    0.44
     phép
    0.43
    Activations Density 0.002%

    No Known Activations