Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74573
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    \{\\
    -0.68
    msgTypes
    -0.67
     ffilmiau
    -0.65
    (!__
    -0.65
     createSlice
    -0.63
     '\\;'
    -0.61
     légales
    -0.60
    StoryboardSegue
    -0.60
     الحره
    -0.58
    >-->
    -0.57
    POSITIVE LOGITS
    TagMode
    0.51
     aveug
    0.45
     conduite
    0.42
    SOUNDBITE
    0.41
     saada
    0.41
    IsMutable
    0.40
     acrylique
    0.40
     vectorielle
    0.38
     negru
    0.38
    ruptedException
    0.38
    Activations Density 0.095%

    No Known Activations