© 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. 5-CLT-HP
    7. 95149
    Prev
    Next
    INDEX
    Explanations

    Of

    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
    Xna
    -0.44
     soup
    -0.41
     surla
    -0.40
     yore
    -0.38
    közi
    -0.38
     ramen
    -0.37
     pasta
    -0.37
    力和
    -0.37
    SX
    -0.36
     ähn
    -0.36
    POSITIVE LOGITS
    webElementXpaths
    0.66
     <<<<<<<<<<<<<<
    0.63
     None
    0.62
    Personendaten
    0.60
    InjectAttribute
    0.60
     saites
    0.60
     Confidential
    0.59
     للاسماء
    0.59
     preferentially
    0.59
    PRNewswire
    0.57
    Activations Density 0.004%

    No Known Activations