© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1588
    Prev
    Next
    INDEX
    Explanations

    differ

    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
     CreateTagHelper
    -0.85
    SequentialGroup
    -0.73
     تضيفلها
    -0.62
    findpost
    -0.62
     EconPapers
    -0.59
     disambiguazione
    -0.59
    Allo
    -0.57
     tartalomajánló
    -0.57
    synthesize
    -0.56
    Personendaten
    -0.56
    POSITIVE LOGITS
     significantly
    0.63
     greatly
    0.56
     materially
    0.55
    significantly
    0.55
     dramatically
    0.54
     substantially
    0.53
     drastically
    0.49
     ervoor
    0.48
     markedly
    0.47
    écution
    0.46
    Activations Density 0.040%

    No Known Activations