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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12755
    Prev
    Next
    INDEX
    Explanations

    structured information

    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
     للمعارف
    -0.58
    ers
    -0.57
    enido
    -0.54
     muualla
    -0.54
    lers
    -0.49
    arial
    -0.49
    DataMember
    -0.47
    er
    -0.46
     byt
    -0.46
     predic
    -0.46
    POSITIVE LOGITS
    IVEREF
    0.66
    MockMvc
    0.61
    didReceive
    0.60
    WebServlet
    0.56
     gyhoeddwyd
    0.55
    ulemon
    0.54
    extAlignment
    0.54
    Демографія
    0.51
     '{}
    0.51
    liosis
    0.51
    Activations Density 0.006%

    No Known Activations