© 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. 4-CLT-HP
    7. 3533
    Prev
    Next
    INDEX
    Explanations

    three

    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
    mobileqq
    -0.43
     głów
    -0.41
    体が
    -0.41
    man
    -0.40
     inilah
    -0.39
     pertama
    -0.39
     a
    -0.38
    ciptakan
    -0.37
    ers
    -0.37
     województwie
    -0.37
    POSITIVE LOGITS
     betweenstory
    0.91
     ExecuteAsync
    0.79
    WebVitals
    0.78
    UnknownFields
    0.75
    Portail
    0.74
    Portale
    0.74
     NSCoder
    0.73
     InputDecoration
    0.71
     يتيمه
    0.69
     Audiodateien
    0.67
    Activations Density 0.045%

    No Known Activations