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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43529
    Prev
    Next
    INDEX
    Explanations

    on-line

    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
     оригіналу
    -0.73
    enumi
    -0.71
    存于互联网档案馆
    -0.70
    IVEREF
    -0.69
    thenReturn
    -0.67
    RefNanny
    -0.67
    +#+
    -0.67
    dolu
    -0.67
    DeleteBehavior
    -0.66
     récon
    -0.66
    POSITIVE LOGITS
     and
    0.47
     deep
    0.45
     cách
    0.44
     pro
    0.44
    setHas
    0.43
     set
    0.43
     ma
    0.42
     or
    0.41
     le
    0.41
     (
    0.41
    Activations Density 0.346%

    No Known Activations