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. 0-CLT-HP
    4. 44598
    Prev
    Next
    INDEX
    Explanations

    disability

    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
     CreateTagHelper
    -1.55
     resourceCulture
    -1.49
     feroit
    -1.41
     auroit
    -1.36
    ergies
    -1.34
     estimés
    -1.34
     propOrder
    -1.33
     pleaſure
    -1.32
    <unused7>
    -1.30
    <unused8>
    -1.30
    POSITIVE LOGITS
    .
    0.83
    ,
    0.78
     of
    0.75
     to
    0.74
     in
    0.71
     (
    0.71
     for
    0.69
     "
    0.66
    ↵↵
    0.65
     the
    0.65
    Activations Density 0.077%

    No Known Activations