© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3367
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    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
    Lähteet
    -0.61
     المعيارى
    -0.54
     Signalez
    -0.54
    FormTagHelper
    -0.53
    ToProps
    -0.50
     kasarigan
    -0.49
     mikro
    -0.47
     Mikro
    -0.45
    îné
    -0.44
    avel
    -0.44
    POSITIVE LOGITS
     endeavour
    0.62
     whim
    0.60
     endeavor
    0.60
     trifling
    0.60
     <<<<<<<<<<<<<<
    0.59
     pursuit
    0.59
     hopes
    0.58
     jest
    0.57
     attempt
    0.57
    awaiter
    0.57
    Activations Density 0.001%

    No Known Activations