© 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. 1-CLT-HP
    7. 1009
    Prev
    Next
    INDEX
    Explanations

    reduction

    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
    StackNavigator
    -0.63
    RTLD
    -0.62
    RTGC
    -0.61
     Normdatei
    -0.59
    клопе
    -0.57
    SharedCtor
    -0.52
     насељу
    -0.52
    Datuak
    -0.51
    FetchType
    -0.50
     EClass
    -0.50
    POSITIVE LOGITS
     indisponible
    0.54
    unesse
    0.48
     goal
    0.47
    ChildScrollView
    0.47
     componen
    0.46
    nale
    0.44
    nau
    0.44
    NavigationView
    0.43
    väg
    0.43
    account
    0.43
    Activations Density 0.029%

    No Known Activations