© 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. 0-CLT-HP
    7. 38934
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
     Efq
    -1.20
     myſelf
    -1.13
     ་་
    -1.04
     Majefty
    -1.03
     itſelf
    -1.02
     Monfieur
    -1.00
     raiſ
    -0.96
     Jefus
    -0.94
     houſe
    -0.94
     Cæsar
    -0.94
    POSITIVE LOGITS
     vi
    0.58
     N
    0.56
     H
    0.56
     I
    0.54
     case
    0.54
     al
    0.52
     $\
    0.50
     et
    0.50
     la
    0.49
     M
    0.49
    Activations Density 0.026%

    No Known Activations