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. 74546
    Prev
    Next
    INDEX
    Explanations

    say PUBLISHED

    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
     незавершена
    -0.57
    ArgsConstructor
    -0.54
    +#+#
    -0.51
    randomUUID
    -0.50
    Predecesor
    -0.49
    ioutil
    -0.49
     ProtoMessage
    -0.49
    庁
    -0.49
     onCancelled
    -0.48
    Eloquent
    -0.48
    POSITIVE LOGITS
    portál
    0.56
    iausi
    0.47
     worry
    0.47
     uwe
    0.47
     excur
    0.47
    izzera
    0.46
    intenant
    0.45
    ConstraintMaker
    0.45
     ostavi
    0.43
    xhttp
    0.43
    Activations Density 0.002%

    No Known Activations