© 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. 43461
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    antası
    -0.58
    Datuak
    -0.54
    раздо
    -0.52
    bibitem
    -0.51
    läufe
    -0.50
    SharedDtor
    -0.50
     ویکی‌پدی
    -0.49
    ार्
    -0.49
    ]();
    -0.49
     to
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.85
     تضيفلها
    0.85
     defaultstate
    0.73
     viewDidLoad
    0.66
    BeginContext
    0.63
     raiſ
    0.59
     groupBox
    0.57
    serde
    0.54
     tarko
    0.53
    ransition
    0.53
    Activations Density 0.032%

    No Known Activations