© 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. 1-CLT-HP
    7. 14288
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    참고
    -0.48
     Plum
    -0.40
     playa
    -0.38
    Plum
    -0.36
    tvguidetime
    -0.36
    TypedDataSet
    -0.36
     anjo
    -0.34
    oredCriteria
    -0.34
     rahat
    -0.34
     couv
    -0.34
    POSITIVE LOGITS
     ProtoMessage
    0.81
    TagMode
    0.67
    følgelig
    0.66
    ífero
    0.66
    AddTagHelper
    0.60
    keiten
    0.60
    ConstraintMaker
    0.60
     springfox
    0.59
    itecture
    0.59
    ighed
    0.59
    Activations Density 0.025%

    No Known Activations