© 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. 43917
    Prev
    Next
    INDEX
    Explanations

    forward

    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
     forward
    -2.63
    Forward
    -2.11
     Forward
    -2.11
    forward
    -2.06
     FORWARD
    -1.98
     forwards
    -1.80
    FORWARD
    -1.61
     вперед
    -1.48
     fwd
    -1.41
     backward
    -1.35
    POSITIVE LOGITS
    ly
    0.67
     للمعارف
    0.57
    er
    0.52
     dus
    0.51
     relâche
    0.48
    ंदीखरीदारी
    0.48
    ter
    0.48
    IRUS
    0.48
    ER
    0.47
    payers
    0.47
    Activations Density 0.045%

    No Known Activations