Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74364
    Prev
    Next
    INDEX
    Explanations

    random text

    np_max-act-logits · 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
     ReactDOM
    -0.77
    ArrowToggle
    -0.73
    queryInterface
    -0.66
     autorytatywna
    -0.61
     BorderSide
    -0.61
     TestBed
    -0.60
     Вікі
    -0.59
     ISNI
    -0.57
    ########.
    -0.57
     surla
    -0.56
    POSITIVE LOGITS
    ey
    0.46
    eara
    0.43
     spécial
    0.40
     Thorpe
    0.40
    ora
    0.39
    oriya
    0.39
    awm
    0.38
     pref
    0.38
    orar
    0.37
    ட்ச
    0.37
    Activations Density 0.000%

    No Known Activations