© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1296
    Prev
    Next
    INDEX
    Explanations

    her

    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
     her
    -0.73
     she
    -0.53
    her
    -0.48
    IsPostBack
    -0.46
     그녀
    -0.44
    彼女の
    -0.43
    quartered
    -0.43
    olari
    -0.43
    cephala
    -0.43
    ьере
    -0.40
    POSITIVE LOGITS
    ValueStyle
    0.77
     ***!
    0.75
    ParallelGroup
    0.73
    tagHelperRunner
    0.70
     cherchés
    0.70
    AddTagHelper
    0.70
     nahilalakip
    0.66
     nakalista
    0.65
    writeFieldEnd
    0.63
    Portail
    0.63
    Activations Density 0.143%

    No Known Activations