© 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. 0-CLT-HP
    7. 41742
    Prev
    Next
    INDEX
    Explanations

    Business/professional services

    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
     NSCoder
    -0.66
     femininas
    -0.61
     sánh
    -0.59
     trusted
    -0.58
     متعلقه
    -0.55
    PYX
    -0.55
    tanleria
    -0.55
     trustworthy
    -0.52
    trusted
    -0.52
    Datuak
    -0.51
    POSITIVE LOGITS
    <bos>
    0.62
    Lähteet
    0.57
     doubtnut
    0.56
     Uint
    0.53
    TagMode
    0.53
     TextFormField
    0.53
     eye
    0.52
     viol
    0.50
     agreement
    0.50
    IndentedString
    0.50
    Activations Density 0.129%

    No Known Activations