© 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. 93881
    Prev
    Next
    INDEX
    Explanations

    the

    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
    fjspx
    -0.50
    zedł
    -0.48
     herself
    -0.47
    mêmes
    -0.47
    Organic
    -0.47
     himself
    -0.46
     ORGANIC
    -0.46
     OFDb
    -0.46
     तह
    -0.46
     Organic
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.80
     MessageBoxIcon
    0.71
    ThroughAttribute
    0.71
     referenties
    0.62
     InputDecoration
    0.57
     nouveautés
    0.57
     يتيمه
    0.56
     doigts
    0.54
    GraphicsUnit
    0.53
     Politiker
    0.52
    Activations Density 0.002%

    No Known Activations