© 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. 0-CLT-HP
    7. 40757
    Prev
    Next
    INDEX
    Explanations

    later

    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
     reprise
    -0.56
    DoubleQuotes
    -0.56
     senare
    -0.55
    though
    -0.54
     remind
    -0.54
     velkommen
    -0.53
     reassure
    -0.52
     FontFamily
    -0.51
    ropriate
    -0.50
     THOUGH
    -0.49
    POSITIVE LOGITS
    TestingModule
    0.68
    GEBURTSDATUM
    0.64
     snippetHide
    0.61
    UnusedPrivate
    0.60
    resave
    0.60
    __':
    0.59
     continúas
    0.59
    NameInMap
    0.59
    StoryboardSegue
    0.57
    webElementXpaths
    0.57
    Activations Density 0.092%

    No Known Activations