Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97934
    Prev
    Next
    INDEX
    Explanations

    descriptions/definitions

    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
     will
    -1.31
    will
    -1.11
     akan
    -1.05
     zullen
    -0.97
    Will
    -0.95
     sẽ
    -0.91
     насељу
    -0.84
    arão
    -0.83
     nonatomic
    -0.82
     خواهند
    -0.81
    POSITIVE LOGITS
     be
    0.83
    ,
    0.62
    .
    0.53
    -
    0.48
    l
    0.47
     not
    0.46
     stand
    0.46
    be
    0.46
     come
    0.45
    '
    0.45
    Activations Density 0.008%

    No Known Activations