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. 73970
    Prev
    Next
    INDEX
    Explanations

    much

    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
    jsxFileName
    -0.73
    tagext
    -0.73
    IUrlHelper
    -0.71
    +#+#
    -0.70
    saraba
    -0.66
    σθαι
    -0.65
     testSet
    -0.64
     barbati
    -0.62
     informée
    -0.61
     tartalomajánló
    -0.61
    POSITIVE LOGITS
     much
    0.95
    Much
    0.90
    much
    0.89
     Much
    0.82
     MUCH
    0.71
     mucho
    0.58
     disponibilités
    0.51
    enumi
    0.48
     viel
    0.48
     mucha
    0.47
    Activations Density 0.001%

    No Known Activations