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. 73835
    Prev
    Next
    INDEX
    Explanations

    ole

    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
    AndEndTag
    -0.57
     NSCoder
    -0.55
    verständlich
    -0.55
    unhofer
    -0.53
    coda
    -0.52
    BagConstraints
    -0.51
    ROIT
    -0.49
     CGRectMake
    -0.48
    CGRectMake
    -0.47
    urel
    -0.46
    POSITIVE LOGITS
    RegistryLite
    0.63
    aarrggbb
    0.62
     CreateTagHelper
    0.59
     tegens
    0.57
    NameInMap
    0.56
     تضيفلها
    0.55
     distanciation
    0.54
    Geplaatst
    0.54
     palmas
    0.51
    Clik
    0.50
    Activations Density 0.004%

    No Known Activations