© 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. 4-CLT-HP
    7. 2466
    Prev
    Next
    INDEX
    Explanations

    business, technology, or government

    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
     powerful
    -1.43
    powerful
    -1.30
     power
    -1.20
    Powerful
    -1.19
     poderosa
    -1.12
     poderoso
    -1.10
     Powerful
    -1.09
     puissant
    -1.09
     poderosos
    -1.05
    power
    -1.03
    POSITIVE LOGITS
    StoryboardSegue
    0.76
    =$?
    0.65
     nahilalakip
    0.65
     مشين
    0.63
     typelib
    0.63
     ―――――
    0.62
     doubtnut
    0.61
     Jefus
    0.59
    djangoproject
    0.59
    .³
    0.58
    Activations Density 0.007%

    No Known Activations