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. 74564
    Prev
    Next
    INDEX
    Explanations

    Citations in research papers

    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
     <=",
    -0.77
     autorytatywna
    -0.73
    AddTagHelper
    -0.73
    ImageContext
    -0.71
    EndProject
    -0.68
     OFDb
    -0.67
     صوتيه
    -0.66
    twimg
    -0.63
    Personendaten
    -0.62
    GOTREF
    -0.61
    POSITIVE LOGITS
    el
    0.41
     rosse
    0.41
    ług
    0.40
     touch
    0.39
     lovers
    0.39
    els
    0.38
     voll
    0.38
    Errorf
    0.37
     fractions
    0.37
     around
    0.36
    Activations Density 0.018%

    No Known Activations