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. 1-CLT-HP
    4. 12890
    Prev
    Next
    INDEX
    Explanations

    number words

    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
    ContentAsync
    -0.86
    VIAF
    -0.81
     propOrder
    -0.75
     autorytatywna
    -0.72
     <=",
    -0.68
     Réponses
    -0.63
     disambiguazione
    -0.63
     ujednoznacz
    -0.61
    зулта
    -0.60
     kasarigan
    -0.60
    POSITIVE LOGITS
    ModelForm
    0.52
     velocity
    0.43
     EPS
    0.43
     comparison
    0.40
     tumour
    0.40
    startAnimation
    0.40
     popularity
    0.39
     PET
    0.38
     hospitals
    0.38
     PoE
    0.38
    Activations Density 0.045%

    No Known Activations