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. 74212
    Prev
    Next
    INDEX
    Explanations

    code/text 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
    setVerticalGroup
    -0.66
     defaultstate
    -0.65
     Soap
    -0.59
    ifoli
    -0.58
    adpleegd
    -0.57
    styleType
    -0.56
     йо
    -0.54
    MessageTagHelper
    -0.54
     distanciation
    -0.53
    CodedInputStream
    -0.52
    POSITIVE LOGITS
    NOPQRST
    0.48
    kras
    0.44
    esgue
    0.44
    qz
    0.43
    VAR
    0.42
    "{\
    0.42
    点は
    0.41
    keres
    0.40
     pulumi
    0.40
     PeEnEo
    0.40
    Activations Density 0.003%

    No Known Activations