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. 12689
    Prev
    Next
    INDEX
    Explanations

    Medical needles and injections

    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
     Needles
    -0.84
     Needle
    -0.81
     needles
    -0.78
    needle
    -0.78
     needle
    -0.78
    Needle
    -0.74
    ificantly
    -0.47
     aguja
    -0.45
    ГЛА
    -0.44
     agujas
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.91
    ConstraintMaker
    0.81
    tagHelperRunner
    0.77
    AsUp
    0.75
     Waray
    0.72
     oprot
    0.68
    UnusedPrivate
    0.68
     '\\;'
    0.68
    Revenir
    0.67
     externi
    0.67
    Activations Density 0.004%

    No Known Activations