© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1214
    Prev
    Next
    INDEX
    Explanations

    only

    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
     last
    -0.59
    ,
    -0.58
     lastly
    -0.57
    fastjson
    -0.55
    #+#
    -0.54
     derni
    -0.53
    Hentet
    -0.53
     protoimpl
    -0.52
     finally
    -0.51
     tromper
    -0.50
    POSITIVE LOGITS
    Hauptartikel
    0.56
     IOError
    0.52
    Datuak
    0.52
     المعيارى
    0.51
     Wikidata
    0.50
    LOCAL
    0.50
    deleteById
    0.49
     nahilalakip
    0.49
     nostalgia
    0.48
    æn
    0.48
    Activations Density 0.013%

    No Known Activations