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. 73865
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ostavi
    -0.59
     HttpHeaders
    -0.49
    andExpect
    -0.47
    TagMode
    -0.47
    initialize
    -0.45
     Organizing
    -0.45
     chers
    -0.44
     lại
    -0.44
    جموع
    -0.43
    ್ದ
    -0.43
    POSITIVE LOGITS
    UnusedPrivate
    0.72
     correct
    0.67
    encodeWith
    0.63
    :+:
    0.55
    SizeMode
    0.53
    存于互联网档案馆
    0.52
    ⇑
    0.52
    {}{}
    0.52
     uintptr
    0.51
    arithmic
    0.51
    Activations Density 0.001%

    No Known Activations