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. 20-CLT-HP
    4. 74312
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    \{\\
    -0.75
     متعلقه
    -0.75
    AndEndTag
    -0.72
    SourceChecksum
    -0.71
     $_"
    -0.70
    tagHelperRunner
    -0.66
    MessageTagHelper
    -0.64
     المعيارى
    -0.63
    batik
    -0.63
    toHaveBeenCalled
    -0.62
    POSITIVE LOGITS
    ids
    0.40
    idov
    0.40
    ida
    0.39
    idis
    0.37
    idor
    0.36
    eces
    0.35
    ache
    0.34
    ēs
    0.34
    idea
    0.34
    ides
    0.34
    Activations Density 0.000%

    No Known Activations