© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97389
    Prev
    Next
    INDEX
    Explanations

    better

    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
     better
    -0.57
    RectangleBorder
    -0.48
    better
    -0.47
     iconFacebook
    -0.47
    importanza
    -0.45
    SequentialGroup
    -0.45
    occasione
    -0.45
    μός
    -0.44
    hips
    -0.44
    esistenza
    -0.43
    POSITIVE LOGITS
    ########.
    0.71
    onViewCreated
    0.69
    ORETICAL
    0.65
     Theoretical
    0.64
     Informatics
    0.64
     referenties
    0.63
     perfusion
    0.62
     Approximation
    0.62
     acuity
    0.62
    XMLSchema
    0.60
    Activations Density 0.064%

    No Known Activations