© 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. 5-CLT-HP
    7. 3252
    Prev
    Next
    INDEX
    Explanations

    3

    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
     betweenstory
    -1.05
     مشين
    -0.99
     nakalista
    -0.97
    DockStyle
    -0.92
    تقاوى
    -0.92
    __':
    -0.90
    
    -0.88
    expandindo
    -0.85
    Hochspringen
    -0.84
    GEBURTSDATUM
    -0.84
    POSITIVE LOGITS
    en
    0.47
     and
    0.42
     turns
    0.42
     /
    0.40
     Wachs
    0.40
    <eos>
    0.39
    /
    0.38
     turned
    0.38
    ens
    0.37
     turning
    0.36
    Activations Density 0.006%

    No Known Activations