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. 74498
    Prev
    Next
    INDEX
    Explanations

    technology and code snippets

    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
    +#+#
    -0.83
     linkovi
    -0.70
    WriteBarrier
    -0.63
     >=",
    -0.60
    Vidite
    -0.59
    misu
    -0.58
    tagHelperRunner
    -0.58
     yellows
    -0.58
    ,:)
    -0.57
    Postup
    -0.56
    POSITIVE LOGITS
     VIAF
    0.58
     v
    0.52
    SerializeField
    0.49
    BeginContext
    0.46
    保
    0.45
     po
    0.42
    npmjs
    0.42
    harma
    0.41
     polling
    0.41
    IEC
    0.41
    Activations Density 0.001%

    No Known Activations