© 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. 96312
    Prev
    Next
    INDEX
    Explanations

    conjunctions, commas

    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
    Autoritní
    -0.93
     autorytatywna
    -0.81
    VersionUID
    -0.75
    MessageOf
    -0.74
    XmlAccessorType
    -0.73
     propOrder
    -0.66
    ConstraintMaker
    -0.63
    RUnlock
    -0.61
     kaarangay
    -0.60
    TagMode
    -0.60
    POSITIVE LOGITS
     adjourned
    0.56
     revised
    0.46
     modified
    0.45
    /@
    0.44
     thêm
    0.44
     better
    0.44
    Sc
    0.42
    IFICATE
    0.40
     становника
    0.39
    acar
    0.39
    Activations Density 0.006%

    No Known Activations