© 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. 20-CLT-HP
    7. 72467
    Prev
    Next
    INDEX
    Explanations

    reporting

    np_max-act-logits · 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
     advise
    -0.94
     suggest
    -0.89
     Suggest
    -0.88
    suggest
    -0.83
     advice
    -0.81
     advises
    -0.77
     warn
    -0.77
    WebVitals
    -0.76
    LayoutStyle
    -0.74
    Suggest
    -0.73
    POSITIVE LOGITS
     متعلقه
    0.50
    olz
    0.45
    Go
    0.44
    onload
    0.43
     assured
    0.43
     Go
    0.42
    ффек
    0.41
     coun
    0.39
     Sport
    0.38
     tu
    0.37
    Activations Density 0.003%

    No Known Activations